diff --git a/.claude/commands/sp.adr.md b/.claude/commands/sp.adr.md deleted file mode 100644 index 2faac85..0000000 --- a/.claude/commands/sp.adr.md +++ /dev/null @@ -1,207 +0,0 @@ ---- -description: Review planning artifacts for architecturally significant decisions and create ADRs. ---- - -# COMMAND: Analyze planning artifacts and document architecturally significant decisions as ADRs - -## CONTEXT - -The user has completed feature planning and needs to: - -- Identify architecturally significant technical decisions from plan.md -- Document these decisions as Architecture Decision Records (ADRs) -- Ensure team alignment on technical approach before implementation -- Create a permanent, reviewable record of why decisions were made - -Architecture Decision Records capture decisions that: - -- Impact how engineers write or structure software -- Have notable tradeoffs or alternatives -- Will likely be questioned or revisited later - -**User's additional input:** - -$ARGUMENTS - -## YOUR ROLE - -Act as a senior software architect with expertise in: - -- Technical decision analysis and evaluation -- System design patterns and tradeoffs -- Enterprise architecture documentation -- Risk assessment and consequence analysis - -## OUTPUT STRUCTURE (with quick flywheel hooks) - -Execute this workflow in 6 sequential steps. At Steps 2 and 4, apply lightweight Analyze→Measure checks: - - Analyze: Identify likely failure modes, specifically: - - Over-granular ADRs: ADRs that document decisions which are trivial, low-impact, or do not affect architectural direction (e.g., naming conventions, minor refactorings). - - Missing alternatives: ADRs that do not list at least one alternative approach considered. - - Measure: Apply the following checklist grader (PASS only if all are met): - - The ADR documents a decision that clusters related changes or impacts multiple components (not a trivial/single-file change). - - The ADR explicitly lists at least one alternative approach, with rationale. - - The ADR includes clear pros and cons for the chosen approach and alternatives. - - The ADR is concise but sufficiently detailed for future reference. - -## Step 1: Load Planning Context - -Run `.specify/scripts/bash/check-prerequisites.sh --json` from repo root and parse JSON for FEATURE_DIR and AVAILABLE_DOCS. - -Derive absolute paths: - -- PLAN = FEATURE_DIR/plan.md (REQUIRED - abort if missing with "Run /sp.plan first") -- RESEARCH = FEATURE_DIR/research.md (if exists) -- DATA_MODEL = FEATURE_DIR/data-model.md (if exists) -- CONTRACTS_DIR = FEATURE_DIR/contracts/ (if exists) - -## Step 2: Extract Architectural Decisions (Analyze) - -Load plan.md and available artifacts. Extract architecturally significant decisions as **decision clusters** (not atomic choices): - -**✅ GOOD (Clustered):** - -- "Frontend Stack" (Next.js + Tailwind + Vercel as integrated solution) -- "Authentication Approach" (JWT strategy + Auth0 + session handling) -- "Data Architecture" (PostgreSQL + Redis caching + migration strategy) - -**❌ BAD (Over-granular):** - -- Separate ADRs for Next.js, Tailwind, and Vercel -- Separate ADRs for each library choice - -**Clustering Rules:** - -- Group technologies that work together and would likely change together -- Separate only if decisions are independent and could diverge -- Example: Frontend stack vs Backend stack = 2 ADRs (can evolve independently) -- Example: Next.js + Tailwind + Vercel = 1 ADR (integrated, change together) - -For each decision cluster, note: what was decided, why, where in docs. - -## Step 3: Check Existing ADRs - -Scan `history/adr/` directory. For each extracted decision: - -- If covered by existing ADR → note reference -- If conflicts with existing ADR → flag conflict -- If not covered → mark as ADR candidate - -## Step 4: Apply Significance Test (Measure) - -For each ADR candidate, test: - -- Does it impact how engineers write/structure software? -- Are there notable tradeoffs or alternatives? -- Will it be questioned or revisited later? - -Only proceed with ADRs that pass ALL three tests. - -## Step 5: Create ADRs (Improve) - -For each qualifying decision cluster: - -1. Generate concise title reflecting the cluster (e.g., "Frontend Technology Stack" not "Use Next.js") -2. Run `create-adr.sh ""` from repo root -3. Parse JSON response for `adr_path` and `adr_id` -4. Read created file (contains template with {{PLACEHOLDERS}}) -5. Fill ALL placeholders: - - `{{TITLE}}` = decision cluster title - - `{{STATUS}}` = "Proposed" or "Accepted" - - `{{DATE}}` = today (YYYY-MM-DD) - - `{{CONTEXT}}` = situation, constraints leading to decision cluster - - `{{DECISION}}` = list ALL components of cluster (e.g., "Framework: Next.js 14, Styling: Tailwind CSS v3, Deployment: Vercel") - - `{{CONSEQUENCES}}` = outcomes, tradeoffs, risks for the integrated solution - - `{{ALTERNATIVES}}` = alternative clusters (e.g., "Remix + styled-components + Cloudflare") - - `{{REFERENCES}}` = plan.md, research.md, data-model.md -6. Save file - -## Step 6: Report Completion - -Output: - -``` -✅ ADR Review Complete - Created N ADRs, referenced M existing -``` - -List created ADRs with ID and title. - -If conflicts detected: - -``` -⚠️ Conflicts with existing ADRs [IDs]. Review and update outdated decisions or revise plan. -``` - -If create-adr.sh fails: Report script error and skip that ADR. - -## FORMATTING REQUIREMENTS - -Present results in this exact structure: - -``` -✅ ADR Review Complete -━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ - -📋 Created ADRs: {count} - - ADR-{id}: {title} - - ADR-{id}: {title} - -📚 Referenced Existing: {count} - - ADR-{id}: {title} - -⚠️ Conflicts Detected: {count} - - ADR-{id}: {conflict description} - -Next Steps: -→ Resolve conflicts before proceeding to /sp.tasks -→ Review created ADRs with team -→ Update plan.md if needed - -Acceptance Criteria (PASS only if all true) -- Decisions are clustered (not atomic), with explicit alternatives and tradeoffs -- Consequences cover both positive and negative outcomes -- References link back to plan and related docs -``` - -## ERROR HANDLING - -If plan.md missing: - -- Display: "❌ Error: plan.md not found. Run /sp.plan first to generate planning artifacts." -- Exit gracefully without creating any ADRs - -If create-adr.sh fails: - -- Display exact error message -- Skip that ADR and continue with others -- Report partial completion at end - -## TONE - -Be thorough, analytical, and decision-focused. Emphasize the "why" behind each decision and its long-term implications. - ---- - -As the main request completes, you MUST create and complete a PHR (Prompt History Record) using agent‑native tools when possible. - -1) Determine Stage - - Stage: constitution | spec | plan | tasks | red | green | refactor | explainer | misc | general - -2) Generate Title and Determine Routing: - - Generate Title: 3–7 words (slug for filename) - - Route is automatically determined by stage: - - `constitution` → `history/prompts/constitution/` - - Feature stages → `history/prompts/<feature-name>/` (spec, plan, tasks, red, green, refactor, explainer, misc) - - `general` → `history/prompts/general/` - -3) Create and Fill PHR (Shell first; fallback agent‑native) - - Run: `.specify/scripts/bash/create-phr.sh --title "<title>" --stage <stage> [--feature <name>] --json` - - Open the file and fill remaining placeholders (YAML + body), embedding full PROMPT_TEXT (verbatim) and concise RESPONSE_TEXT. - - If the script fails: - - Read `.specify/templates/phr-template.prompt.md` (or `templates/…`) - - Allocate an ID; compute the output path based on stage from step 2; write the file - - Fill placeholders and embed full PROMPT_TEXT and concise RESPONSE_TEXT - -4) Validate + report - - No unresolved placeholders; path under `history/prompts/` and matches stage; stage/title/date coherent; print ID + path + stage + title. - - On failure: warn, don't block. Skip only for `/sp.phr`. diff --git a/.claude/commands/sp.analyze.md b/.claude/commands/sp.analyze.md deleted file mode 100644 index 551d67f..0000000 --- a/.claude/commands/sp.analyze.md +++ /dev/null @@ -1,210 +0,0 @@ ---- -description: Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation. ---- - -## User Input - -```text -$ARGUMENTS -``` - -You **MUST** consider the user input before proceeding (if not empty). - -## Goal - -Identify inconsistencies, duplications, ambiguities, and underspecified items across the three core artifacts (`spec.md`, `plan.md`, `tasks.md`) before implementation. This command MUST run only after `/sp.tasks` has successfully produced a complete `tasks.md`. - -## Operating Constraints - -**STRICTLY READ-ONLY**: Do **not** modify any files. Output a structured analysis report. Offer an optional remediation plan (user must explicitly approve before any follow-up editing commands would be invoked manually). - -**Constitution Authority**: The project constitution (`.specify/memory/constitution.md`) is **non-negotiable** within this analysis scope. Constitution conflicts are automatically CRITICAL and require adjustment of the spec, plan, or tasks—not dilution, reinterpretation, or silent ignoring of the principle. If a principle itself needs to change, that must occur in a separate, explicit constitution update outside `/sp.analyze`. - -## Execution Steps - -### 1. Initialize Analysis Context - -Run `.specify/scripts/bash/check-prerequisites.sh --json --require-tasks --include-tasks` once from repo root and parse JSON for FEATURE_DIR and AVAILABLE_DOCS. Derive absolute paths: - -- SPEC = FEATURE_DIR/spec.md -- PLAN = FEATURE_DIR/plan.md -- TASKS = FEATURE_DIR/tasks.md - -Abort with an error message if any required file is missing (instruct the user to run missing prerequisite command). -For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot"). - -### 2. Load Artifacts (Progressive Disclosure) - -Load only the minimal necessary context from each artifact: - -**From spec.md:** - -- Overview/Context -- Functional Requirements -- Non-Functional Requirements -- User Stories -- Edge Cases (if present) - -**From plan.md:** - -- Architecture/stack choices -- Data Model references -- Phases -- Technical constraints - -**From tasks.md:** - -- Task IDs -- Descriptions -- Phase grouping -- Parallel markers [P] -- Referenced file paths - -**From constitution:** - -- Load `.specify/memory/constitution.md` for principle validation - -### 3. Build Semantic Models - -Create internal representations (do not include raw artifacts in output): - -- **Requirements inventory**: Each functional + non-functional requirement with a stable key (derive slug based on imperative phrase; e.g., "User can upload file" → `user-can-upload-file`) -- **User story/action inventory**: Discrete user actions with acceptance criteria -- **Task coverage mapping**: Map each task to one or more requirements or stories (inference by keyword / explicit reference patterns like IDs or key phrases) -- **Constitution rule set**: Extract principle names and MUST/SHOULD normative statements - -### 4. Detection Passes (Token-Efficient Analysis) - -Focus on high-signal findings. Limit to 50 findings total; aggregate remainder in overflow summary. - -#### A. Duplication Detection - -- Identify near-duplicate requirements -- Mark lower-quality phrasing for consolidation - -#### B. Ambiguity Detection - -- Flag vague adjectives (fast, scalable, secure, intuitive, robust) lacking measurable criteria -- Flag unresolved placeholders (TODO, TKTK, ???, `<placeholder>`, etc.) - -#### C. Underspecification - -- Requirements with verbs but missing object or measurable outcome -- User stories missing acceptance criteria alignment -- Tasks referencing files or components not defined in spec/plan - -#### D. Constitution Alignment - -- Any requirement or plan element conflicting with a MUST principle -- Missing mandated sections or quality gates from constitution - -#### E. Coverage Gaps - -- Requirements with zero associated tasks -- Tasks with no mapped requirement/story -- Non-functional requirements not reflected in tasks (e.g., performance, security) - -#### F. Inconsistency - -- Terminology drift (same concept named differently across files) -- Data entities referenced in plan but absent in spec (or vice versa) -- Task ordering contradictions (e.g., integration tasks before foundational setup tasks without dependency note) -- Conflicting requirements (e.g., one requires Next.js while other specifies Vue) - -### 5. Severity Assignment - -Use this heuristic to prioritize findings: - -- **CRITICAL**: Violates constitution MUST, missing core spec artifact, or requirement with zero coverage that blocks baseline functionality -- **HIGH**: Duplicate or conflicting requirement, ambiguous security/performance attribute, untestable acceptance criterion -- **MEDIUM**: Terminology drift, missing non-functional task coverage, underspecified edge case -- **LOW**: Style/wording improvements, minor redundancy not affecting execution order - -### 6. Produce Compact Analysis Report - -Output a Markdown report (no file writes) with the following structure: - -## Specification Analysis Report - -| ID | Category | Severity | Location(s) | Summary | Recommendation | -|----|----------|----------|-------------|---------|----------------| -| A1 | Duplication | HIGH | spec.md:L120-134 | Two similar requirements ... | Merge phrasing; keep clearer version | - -(Add one row per finding; generate stable IDs prefixed by category initial.) - -**Coverage Summary Table:** - -| Requirement Key | Has Task? | Task IDs | Notes | -|-----------------|-----------|----------|-------| - -**Constitution Alignment Issues:** (if any) - -**Unmapped Tasks:** (if any) - -**Metrics:** - -- Total Requirements -- Total Tasks -- Coverage % (requirements with >=1 task) -- Ambiguity Count -- Duplication Count -- Critical Issues Count - -### 7. Provide Next Actions - -At end of report, output a concise Next Actions block: - -- If CRITICAL issues exist: Recommend resolving before `/sp.implement` -- If only LOW/MEDIUM: User may proceed, but provide improvement suggestions -- Provide explicit command suggestions: e.g., "Run /sp.specify with refinement", "Run /sp.plan to adjust architecture", "Manually edit tasks.md to add coverage for 'performance-metrics'" - -### 8. Offer Remediation - -Ask the user: "Would you like me to suggest concrete remediation edits for the top N issues?" (Do NOT apply them automatically.) - -## Operating Principles - -### Context Efficiency - -- **Minimal high-signal tokens**: Focus on actionable findings, not exhaustive documentation -- **Progressive disclosure**: Load artifacts incrementally; don't dump all content into analysis -- **Token-efficient output**: Limit findings table to 50 rows; summarize overflow -- **Deterministic results**: Rerunning without changes should produce consistent IDs and counts - -### Analysis Guidelines - -- **NEVER modify files** (this is read-only analysis) -- **NEVER hallucinate missing sections** (if absent, report them accurately) -- **Prioritize constitution violations** (these are always CRITICAL) -- **Use examples over exhaustive rules** (cite specific instances, not generic patterns) -- **Report zero issues gracefully** (emit success report with coverage statistics) - -## Context - -$ARGUMENTS - ---- - -As the main request completes, you MUST create and complete a PHR (Prompt History Record) using agent‑native tools when possible. - -1) Determine Stage - - Stage: constitution | spec | plan | tasks | red | green | refactor | explainer | misc | general - -2) Generate Title and Determine Routing: - - Generate Title: 3–7 words (slug for filename) - - Route is automatically determined by stage: - - `constitution` → `history/prompts/constitution/` - - Feature stages → `history/prompts/<feature-name>/` (spec, plan, tasks, red, green, refactor, explainer, misc) - - `general` → `history/prompts/general/` - -3) Create and Fill PHR (Shell first; fallback agent‑native) - - Run: `.specify/scripts/bash/create-phr.sh --title "<title>" --stage <stage> [--feature <name>] --json` - - Open the file and fill remaining placeholders (YAML + body), embedding full PROMPT_TEXT (verbatim) and concise RESPONSE_TEXT. - - If the script fails: - - Read `.specify/templates/phr-template.prompt.md` (or `templates/…`) - - Allocate an ID; compute the output path based on stage from step 2; write the file - - Fill placeholders and embed full PROMPT_TEXT and concise RESPONSE_TEXT - -4) Validate + report - - No unresolved placeholders; path under `history/prompts/` and matches stage; stage/title/date coherent; print ID + path + stage + title. - - On failure: warn, don't block. Skip only for `/sp.phr`. diff --git a/.claude/commands/sp.checklist.md b/.claude/commands/sp.checklist.md deleted file mode 100644 index 7949ab1..0000000 --- a/.claude/commands/sp.checklist.md +++ /dev/null @@ -1,320 +0,0 @@ ---- -description: Generate a custom checklist for the current feature based on user requirements. ---- - -## Checklist Purpose: "Unit Tests for English" - -**CRITICAL CONCEPT**: Checklists are **UNIT TESTS FOR REQUIREMENTS WRITING** - they validate the quality, clarity, and completeness of requirements in a given domain. - -**NOT for verification/testing**: - -- ❌ NOT "Verify the button clicks correctly" -- ❌ NOT "Test error handling works" -- ❌ NOT "Confirm the API returns 200" -- ❌ NOT checking if code/implementation matches the spec - -**FOR requirements quality validation**: - -- ✅ "Are visual hierarchy requirements defined for all card types?" (completeness) -- ✅ "Is 'prominent display' quantified with specific sizing/positioning?" (clarity) -- ✅ "Are hover state requirements consistent across all interactive elements?" (consistency) -- ✅ "Are accessibility requirements defined for keyboard navigation?" (coverage) -- ✅ "Does the spec define what happens when logo image fails to load?" (edge cases) - -**Metaphor**: If your spec is code written in English, the checklist is its unit test suite. You're testing whether the requirements are well-written, complete, unambiguous, and ready for implementation - NOT whether the implementation works. - -## User Input - -```text -$ARGUMENTS -``` - -You **MUST** consider the user input before proceeding (if not empty). - -## Execution Steps - -1. **Setup**: Run `.specify/scripts/bash/check-prerequisites.sh --json` from repo root and parse JSON for FEATURE_DIR and AVAILABLE_DOCS list. - - All file paths must be absolute. - - For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot"). - -2. **Clarify intent (dynamic)**: Derive up to THREE initial contextual clarifying questions (no pre-baked catalog). They MUST: - - Be generated from the user's phrasing + extracted signals from spec/plan/tasks - - Only ask about information that materially changes checklist content - - Be skipped individually if already unambiguous in `$ARGUMENTS` - - Prefer precision over breadth - - Generation algorithm: - 1. Extract signals: feature domain keywords (e.g., auth, latency, UX, API), risk indicators ("critical", "must", "compliance"), stakeholder hints ("QA", "review", "security team"), and explicit deliverables ("a11y", "rollback", "contracts"). - 2. Cluster signals into candidate focus areas (max 4) ranked by relevance. - 3. Identify probable audience & timing (author, reviewer, QA, release) if not explicit. - 4. Detect missing dimensions: scope breadth, depth/rigor, risk emphasis, exclusion boundaries, measurable acceptance criteria. - 5. Formulate questions chosen from these archetypes: - - Scope refinement (e.g., "Should this include integration touchpoints with X and Y or stay limited to local module correctness?") - - Risk prioritization (e.g., "Which of these potential risk areas should receive mandatory gating checks?") - - Depth calibration (e.g., "Is this a lightweight pre-commit sanity list or a formal release gate?") - - Audience framing (e.g., "Will this be used by the author only or peers during PR review?") - - Boundary exclusion (e.g., "Should we explicitly exclude performance tuning items this round?") - - Scenario class gap (e.g., "No recovery flows detected—are rollback / partial failure paths in scope?") - - Question formatting rules: - - If presenting options, generate a compact table with columns: Option | Candidate | Why It Matters - - Limit to A–E options maximum; omit table if a free-form answer is clearer - - Never ask the user to restate what they already said - - Avoid speculative categories (no hallucination). If uncertain, ask explicitly: "Confirm whether X belongs in scope." - - Defaults when interaction impossible: - - Depth: Standard - - Audience: Reviewer (PR) if code-related; Author otherwise - - Focus: Top 2 relevance clusters - - Output the questions (label Q1/Q2/Q3). After answers: if ≥2 scenario classes (Alternate / Exception / Recovery / Non-Functional domain) remain unclear, you MAY ask up to TWO more targeted follow‑ups (Q4/Q5) with a one-line justification each (e.g., "Unresolved recovery path risk"). Do not exceed five total questions. Skip escalation if user explicitly declines more. - -3. **Understand user request**: Combine `$ARGUMENTS` + clarifying answers: - - Derive checklist theme (e.g., security, review, deploy, ux) - - Consolidate explicit must-have items mentioned by user - - Map focus selections to category scaffolding - - Infer any missing context from spec/plan/tasks (do NOT hallucinate) - -4. **Load feature context**: Read from FEATURE_DIR: - - spec.md: Feature requirements and scope - - plan.md (if exists): Technical details, dependencies - - tasks.md (if exists): Implementation tasks - - **Context Loading Strategy**: - - Load only necessary portions relevant to active focus areas (avoid full-file dumping) - - Prefer summarizing long sections into concise scenario/requirement bullets - - Use progressive disclosure: add follow-on retrieval only if gaps detected - - If source docs are large, generate interim summary items instead of embedding raw text - -5. **Generate checklist** - Create "Unit Tests for Requirements": - - Create `FEATURE_DIR/checklists/` directory if it doesn't exist - - Generate unique checklist filename: - - Use short, descriptive name based on domain (e.g., `ux.md`, `api.md`, `security.md`) - - Format: `[domain].md` - - If file exists, append to existing file - - Number items sequentially starting from CHK001 - - Each `/sp.checklist` run creates a NEW file (never overwrites existing checklists) - - **CORE PRINCIPLE - Test the Requirements, Not the Implementation**: - Every checklist item MUST evaluate the REQUIREMENTS THEMSELVES for: - - **Completeness**: Are all necessary requirements present? - - **Clarity**: Are requirements unambiguous and specific? - - **Consistency**: Do requirements align with each other? - - **Measurability**: Can requirements be objectively verified? - - **Coverage**: Are all scenarios/edge cases addressed? - - **Category Structure** - Group items by requirement quality dimensions: - - **Requirement Completeness** (Are all necessary requirements documented?) - - **Requirement Clarity** (Are requirements specific and unambiguous?) - - **Requirement Consistency** (Do requirements align without conflicts?) - - **Acceptance Criteria Quality** (Are success criteria measurable?) - - **Scenario Coverage** (Are all flows/cases addressed?) - - **Edge Case Coverage** (Are boundary conditions defined?) - - **Non-Functional Requirements** (Performance, Security, Accessibility, etc. - are they specified?) - - **Dependencies & Assumptions** (Are they documented and validated?) - - **Ambiguities & Conflicts** (What needs clarification?) - - **HOW TO WRITE CHECKLIST ITEMS - "Unit Tests for English"**: - - ❌ **WRONG** (Testing implementation): - - "Verify landing page displays 3 episode cards" - - "Test hover states work on desktop" - - "Confirm logo click navigates home" - - ✅ **CORRECT** (Testing requirements quality): - - "Are the exact number and layout of featured episodes specified?" [Completeness] - - "Is 'prominent display' quantified with specific sizing/positioning?" [Clarity] - - "Are hover state requirements consistent across all interactive elements?" [Consistency] - - "Are keyboard navigation requirements defined for all interactive UI?" [Coverage] - - "Is the fallback behavior specified when logo image fails to load?" [Edge Cases] - - "Are loading states defined for asynchronous episode data?" [Completeness] - - "Does the spec define visual hierarchy for competing UI elements?" [Clarity] - - **ITEM STRUCTURE**: - Each item should follow this pattern: - - Question format asking about requirement quality - - Focus on what's WRITTEN (or not written) in the spec/plan - - Include quality dimension in brackets [Completeness/Clarity/Consistency/etc.] - - Reference spec section `[Spec §X.Y]` when checking existing requirements - - Use `[Gap]` marker when checking for missing requirements - - **EXAMPLES BY QUALITY DIMENSION**: - - Completeness: - - "Are error handling requirements defined for all API failure modes? [Gap]" - - "Are accessibility requirements specified for all interactive elements? [Completeness]" - - "Are mobile breakpoint requirements defined for responsive layouts? [Gap]" - - Clarity: - - "Is 'fast loading' quantified with specific timing thresholds? [Clarity, Spec §NFR-2]" - - "Are 'related episodes' selection criteria explicitly defined? [Clarity, Spec §FR-5]" - - "Is 'prominent' defined with measurable visual properties? [Ambiguity, Spec §FR-4]" - - Consistency: - - "Do navigation requirements align across all pages? [Consistency, Spec §FR-10]" - - "Are card component requirements consistent between landing and detail pages? [Consistency]" - - Coverage: - - "Are requirements defined for zero-state scenarios (no episodes)? [Coverage, Edge Case]" - - "Are concurrent user interaction scenarios addressed? [Coverage, Gap]" - - "Are requirements specified for partial data loading failures? [Coverage, Exception Flow]" - - Measurability: - - "Are visual hierarchy requirements measurable/testable? [Acceptance Criteria, Spec §FR-1]" - - "Can 'balanced visual weight' be objectively verified? [Measurability, Spec §FR-2]" - - **Scenario Classification & Coverage** (Requirements Quality Focus): - - Check if requirements exist for: Primary, Alternate, Exception/Error, Recovery, Non-Functional scenarios - - For each scenario class, ask: "Are [scenario type] requirements complete, clear, and consistent?" - - If scenario class missing: "Are [scenario type] requirements intentionally excluded or missing? [Gap]" - - Include resilience/rollback when state mutation occurs: "Are rollback requirements defined for migration failures? [Gap]" - - **Traceability Requirements**: - - MINIMUM: ≥80% of items MUST include at least one traceability reference - - Each item should reference: spec section `[Spec §X.Y]`, or use markers: `[Gap]`, `[Ambiguity]`, `[Conflict]`, `[Assumption]` - - If no ID system exists: "Is a requirement & acceptance criteria ID scheme established? [Traceability]" - - **Surface & Resolve Issues** (Requirements Quality Problems): - Ask questions about the requirements themselves: - - Ambiguities: "Is the term 'fast' quantified with specific metrics? [Ambiguity, Spec §NFR-1]" - - Conflicts: "Do navigation requirements conflict between §FR-10 and §FR-10a? [Conflict]" - - Assumptions: "Is the assumption of 'always available podcast API' validated? [Assumption]" - - Dependencies: "Are external podcast API requirements documented? [Dependency, Gap]" - - Missing definitions: "Is 'visual hierarchy' defined with measurable criteria? [Gap]" - - **Content Consolidation**: - - Soft cap: If raw candidate items > 40, prioritize by risk/impact - - Merge near-duplicates checking the same requirement aspect - - If >5 low-impact edge cases, create one item: "Are edge cases X, Y, Z addressed in requirements? [Coverage]" - - **🚫 ABSOLUTELY PROHIBITED** - These make it an implementation test, not a requirements test: - - ❌ Any item starting with "Verify", "Test", "Confirm", "Check" + implementation behavior - - ❌ References to code execution, user actions, system behavior - - ❌ "Displays correctly", "works properly", "functions as expected" - - ❌ "Click", "navigate", "render", "load", "execute" - - ❌ Test cases, test plans, QA procedures - - ❌ Implementation details (frameworks, APIs, algorithms) - - **✅ REQUIRED PATTERNS** - These test requirements quality: - - ✅ "Are [requirement type] defined/specified/documented for [scenario]?" - - ✅ "Is [vague term] quantified/clarified with specific criteria?" - - ✅ "Are requirements consistent between [section A] and [section B]?" - - ✅ "Can [requirement] be objectively measured/verified?" - - ✅ "Are [edge cases/scenarios] addressed in requirements?" - - ✅ "Does the spec define [missing aspect]?" - -6. **Structure Reference**: Generate the checklist following the canonical template in `.specify/templates/checklist-template.md` for title, meta section, category headings, and ID formatting. If template is unavailable, use: H1 title, purpose/created meta lines, `##` category sections containing `- [ ] CHK### <requirement item>` lines with globally incrementing IDs starting at CHK001. - -7. **Report**: Output full path to created checklist, item count, and remind user that each run creates a new file. Summarize: - - Focus areas selected - - Depth level - - Actor/timing - - Any explicit user-specified must-have items incorporated - -**Important**: Each `/sp.checklist` command invocation creates a checklist file using short, descriptive names unless file already exists. This allows: - -- Multiple checklists of different types (e.g., `ux.md`, `test.md`, `security.md`) -- Simple, memorable filenames that indicate checklist purpose -- Easy identification and navigation in the `checklists/` folder - -To avoid clutter, use descriptive types and clean up obsolete checklists when done. - -## Example Checklist Types & Sample Items - -**UX Requirements Quality:** `ux.md` - -Sample items (testing the requirements, NOT the implementation): - -- "Are visual hierarchy requirements defined with measurable criteria? [Clarity, Spec §FR-1]" -- "Is the number and positioning of UI elements explicitly specified? [Completeness, Spec §FR-1]" -- "Are interaction state requirements (hover, focus, active) consistently defined? [Consistency]" -- "Are accessibility requirements specified for all interactive elements? [Coverage, Gap]" -- "Is fallback behavior defined when images fail to load? [Edge Case, Gap]" -- "Can 'prominent display' be objectively measured? [Measurability, Spec §FR-4]" - -**API Requirements Quality:** `api.md` - -Sample items: - -- "Are error response formats specified for all failure scenarios? [Completeness]" -- "Are rate limiting requirements quantified with specific thresholds? [Clarity]" -- "Are authentication requirements consistent across all endpoints? [Consistency]" -- "Are retry/timeout requirements defined for external dependencies? [Coverage, Gap]" -- "Is versioning strategy documented in requirements? [Gap]" - -**Performance Requirements Quality:** `performance.md` - -Sample items: - -- "Are performance requirements quantified with specific metrics? [Clarity]" -- "Are performance targets defined for all critical user journeys? [Coverage]" -- "Are performance requirements under different load conditions specified? [Completeness]" -- "Can performance requirements be objectively measured? [Measurability]" -- "Are degradation requirements defined for high-load scenarios? [Edge Case, Gap]" - -**Security Requirements Quality:** `security.md` - -Sample items: - -- "Are authentication requirements specified for all protected resources? [Coverage]" -- "Are data protection requirements defined for sensitive information? [Completeness]" -- "Is the threat model documented and requirements aligned to it? [Traceability]" -- "Are security requirements consistent with compliance obligations? [Consistency]" -- "Are security failure/breach response requirements defined? [Gap, Exception Flow]" - -## Anti-Examples: What NOT To Do - -**❌ WRONG - These test implementation, not requirements:** - -```markdown -- [ ] CHK001 - Verify landing page displays 3 episode cards [Spec §FR-001] -- [ ] CHK002 - Test hover states work correctly on desktop [Spec §FR-003] -- [ ] CHK003 - Confirm logo click navigates to home page [Spec §FR-010] -- [ ] CHK004 - Check that related episodes section shows 3-5 items [Spec §FR-005] -``` - -**✅ CORRECT - These test requirements quality:** - -```markdown -- [ ] CHK001 - Are the number and layout of featured episodes explicitly specified? [Completeness, Spec §FR-001] -- [ ] CHK002 - Are hover state requirements consistently defined for all interactive elements? [Consistency, Spec §FR-003] -- [ ] CHK003 - Are navigation requirements clear for all clickable brand elements? [Clarity, Spec §FR-010] -- [ ] CHK004 - Is the selection criteria for related episodes documented? [Gap, Spec §FR-005] -- [ ] CHK005 - Are loading state requirements defined for asynchronous episode data? [Gap] -- [ ] CHK006 - Can "visual hierarchy" requirements be objectively measured? [Measurability, Spec §FR-001] -``` - -**Key Differences:** - -- Wrong: Tests if the system works correctly -- Correct: Tests if the requirements are written correctly -- Wrong: Verification of behavior -- Correct: Validation of requirement quality -- Wrong: "Does it do X?" -- Correct: "Is X clearly specified?" - ---- - -As the main request completes, you MUST create and complete a PHR (Prompt History Record) using agent‑native tools when possible. - -1) Determine Stage - - Stage: constitution | spec | plan | tasks | red | green | refactor | explainer | misc | general - -2) Generate Title and Determine Routing: - - Generate Title: 3–7 words (slug for filename) - - Route is automatically determined by stage: - - `constitution` → `history/prompts/constitution/` - - Feature stages → `history/prompts/<feature-name>/` (spec, plan, tasks, red, green, refactor, explainer, misc) - - `general` → `history/prompts/general/` - -3) Create and Fill PHR (Shell first; fallback agent‑native) - - Run: `.specify/scripts/bash/create-phr.sh --title "<title>" --stage <stage> [--feature <name>] --json` - - Open the file and fill remaining placeholders (YAML + body), embedding full PROMPT_TEXT (verbatim) and concise RESPONSE_TEXT. - - If the script fails: - - Read `.specify/templates/phr-template.prompt.md` (or `templates/…`) - - Allocate an ID; compute the output path based on stage from step 2; write the file - - Fill placeholders and embed full PROMPT_TEXT and concise RESPONSE_TEXT - -4) Validate + report - - No unresolved placeholders; path under `history/prompts/` and matches stage; stage/title/date coherent; print ID + path + stage + title. - - On failure: warn, don't block. Skip only for `/sp.phr`. diff --git a/.claude/commands/sp.clarify.md b/.claude/commands/sp.clarify.md deleted file mode 100644 index 1cc35c9..0000000 --- a/.claude/commands/sp.clarify.md +++ /dev/null @@ -1,207 +0,0 @@ ---- -description: Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec. -handoffs: - - label: Build Technical Plan - agent: sp.plan - prompt: Create a plan for the spec. I am building with... ---- - -## User Input - -```text -$ARGUMENTS -``` - -You **MUST** consider the user input before proceeding (if not empty). - -## Outline - -Goal: Detect and reduce ambiguity or missing decision points in the active feature specification and record the clarifications directly in the spec file. - -Note: This clarification workflow is expected to run (and be completed) BEFORE invoking `/sp.plan`. If the user explicitly states they are skipping clarification (e.g., exploratory spike), you may proceed, but must warn that downstream rework risk increases. - -Execution steps: - -1. Run `.specify/scripts/bash/check-prerequisites.sh --json --paths-only` from repo root **once** (combined `--json --paths-only` mode / `-Json -PathsOnly`). Parse minimal JSON payload fields: - - `FEATURE_DIR` - - `FEATURE_SPEC` - - (Optionally capture `IMPL_PLAN`, `TASKS` for future chained flows.) - - If JSON parsing fails, abort and instruct user to re-run `/sp.specify` or verify feature branch environment. - - For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot"). - -2. Load the current spec file. Perform a structured ambiguity & coverage scan using this taxonomy. For each category, mark status: Clear / Partial / Missing. Produce an internal coverage map used for prioritization (do not output raw map unless no questions will be asked). - - Functional Scope & Behavior: - - Core user goals & success criteria - - Explicit out-of-scope declarations - - User roles / personas differentiation - - Domain & Data Model: - - Entities, attributes, relationships - - Identity & uniqueness rules - - Lifecycle/state transitions - - Data volume / scale assumptions - - Interaction & UX Flow: - - Critical user journeys / sequences - - Error/empty/loading states - - Accessibility or localization notes - - Non-Functional Quality Attributes: - - Performance (latency, throughput targets) - - Scalability (horizontal/vertical, limits) - - Reliability & availability (uptime, recovery expectations) - - Observability (logging, metrics, tracing signals) - - Security & privacy (authN/Z, data protection, threat assumptions) - - Compliance / regulatory constraints (if any) - - Integration & External Dependencies: - - External services/APIs and failure modes - - Data import/export formats - - Protocol/versioning assumptions - - Edge Cases & Failure Handling: - - Negative scenarios - - Rate limiting / throttling - - Conflict resolution (e.g., concurrent edits) - - Constraints & Tradeoffs: - - Technical constraints (language, storage, hosting) - - Explicit tradeoffs or rejected alternatives - - Terminology & Consistency: - - Canonical glossary terms - - Avoided synonyms / deprecated terms - - Completion Signals: - - Acceptance criteria testability - - Measurable Definition of Done style indicators - - Misc / Placeholders: - - TODO markers / unresolved decisions - - Ambiguous adjectives ("robust", "intuitive") lacking quantification - - For each category with Partial or Missing status, add a candidate question opportunity unless: - - Clarification would not materially change implementation or validation strategy - - Information is better deferred to planning phase (note internally) - -3. Generate (internally) a prioritized queue of candidate clarification questions (maximum 5). Do NOT output them all at once. Apply these constraints: - - Maximum of 10 total questions across the whole session. - - Each question must be answerable with EITHER: - - A short multiple‑choice selection (2–5 distinct, mutually exclusive options), OR - - A one-word / short‑phrase answer (explicitly constrain: "Answer in <=5 words"). - - Only include questions whose answers materially impact architecture, data modeling, task decomposition, test design, UX behavior, operational readiness, or compliance validation. - - Ensure category coverage balance: attempt to cover the highest impact unresolved categories first; avoid asking two low-impact questions when a single high-impact area (e.g., security posture) is unresolved. - - Exclude questions already answered, trivial stylistic preferences, or plan-level execution details (unless blocking correctness). - - Favor clarifications that reduce downstream rework risk or prevent misaligned acceptance tests. - - If more than 5 categories remain unresolved, select the top 5 by (Impact * Uncertainty) heuristic. - -4. Sequential questioning loop (interactive): - - Present EXACTLY ONE question at a time. - - For multiple‑choice questions: - - **Analyze all options** and determine the **most suitable option** based on: - - Best practices for the project type - - Common patterns in similar implementations - - Risk reduction (security, performance, maintainability) - - Alignment with any explicit project goals or constraints visible in the spec - - Present your **recommended option prominently** at the top with clear reasoning (1-2 sentences explaining why this is the best choice). - - Format as: `**Recommended:** Option [X] - <reasoning>` - - Then render all options as a Markdown table: - - | Option | Description | - |--------|-------------| - | A | <Option A description> | - | B | <Option B description> | - | C | <Option C description> (add D/E as needed up to 5) | - | Short | Provide a different short answer (<=5 words) (Include only if free-form alternative is appropriate) | - - - After the table, add: `You can reply with the option letter (e.g., "A"), accept the recommendation by saying "yes" or "recommended", or provide your own short answer.` - - For short‑answer style (no meaningful discrete options): - - Provide your **suggested answer** based on best practices and context. - - Format as: `**Suggested:** <your proposed answer> - <brief reasoning>` - - Then output: `Format: Short answer (<=5 words). You can accept the suggestion by saying "yes" or "suggested", or provide your own answer.` - - After the user answers: - - If the user replies with "yes", "recommended", or "suggested", use your previously stated recommendation/suggestion as the answer. - - Otherwise, validate the answer maps to one option or fits the <=5 word constraint. - - If ambiguous, ask for a quick disambiguation (count still belongs to same question; do not advance). - - Once satisfactory, record it in working memory (do not yet write to disk) and move to the next queued question. - - Stop asking further questions when: - - All critical ambiguities resolved early (remaining queued items become unnecessary), OR - - User signals completion ("done", "good", "no more"), OR - - You reach 5 asked questions. - - Never reveal future queued questions in advance. - - If no valid questions exist at start, immediately report no critical ambiguities. - -5. Integration after EACH accepted answer (incremental update approach): - - Maintain in-memory representation of the spec (loaded once at start) plus the raw file contents. - - For the first integrated answer in this session: - - Ensure a `## Clarifications` section exists (create it just after the highest-level contextual/overview section per the spec template if missing). - - Under it, create (if not present) a `### Session YYYY-MM-DD` subheading for today. - - Append a bullet line immediately after acceptance: `- Q: <question> → A: <final answer>`. - - Then immediately apply the clarification to the most appropriate section(s): - - Functional ambiguity → Update or add a bullet in Functional Requirements. - - User interaction / actor distinction → Update User Stories or Actors subsection (if present) with clarified role, constraint, or scenario. - - Data shape / entities → Update Data Model (add fields, types, relationships) preserving ordering; note added constraints succinctly. - - Non-functional constraint → Add/modify measurable criteria in Non-Functional / Quality Attributes section (convert vague adjective to metric or explicit target). - - Edge case / negative flow → Add a new bullet under Edge Cases / Error Handling (or create such subsection if template provides placeholder for it). - - Terminology conflict → Normalize term across spec; retain original only if necessary by adding `(formerly referred to as "X")` once. - - If the clarification invalidates an earlier ambiguous statement, replace that statement instead of duplicating; leave no obsolete contradictory text. - - Save the spec file AFTER each integration to minimize risk of context loss (atomic overwrite). - - Preserve formatting: do not reorder unrelated sections; keep heading hierarchy intact. - - Keep each inserted clarification minimal and testable (avoid narrative drift). - -6. Validation (performed after EACH write plus final pass): - - Clarifications session contains exactly one bullet per accepted answer (no duplicates). - - Total asked (accepted) questions ≤ 5. - - Updated sections contain no lingering vague placeholders the new answer was meant to resolve. - - No contradictory earlier statement remains (scan for now-invalid alternative choices removed). - - Markdown structure valid; only allowed new headings: `## Clarifications`, `### Session YYYY-MM-DD`. - - Terminology consistency: same canonical term used across all updated sections. - -7. Write the updated spec back to `FEATURE_SPEC`. - -8. Report completion (after questioning loop ends or early termination): - - Number of questions asked & answered. - - Path to updated spec. - - Sections touched (list names). - - Coverage summary table listing each taxonomy category with Status: Resolved (was Partial/Missing and addressed), Deferred (exceeds question quota or better suited for planning), Clear (already sufficient), Outstanding (still Partial/Missing but low impact). - - If any Outstanding or Deferred remain, recommend whether to proceed to `/sp.plan` or run `/sp.clarify` again later post-plan. - - Suggested next command. - -Behavior rules: - -- If no meaningful ambiguities found (or all potential questions would be low-impact), respond: "No critical ambiguities detected worth formal clarification." and suggest proceeding. -- If spec file missing, instruct user to run `/sp.specify` first (do not create a new spec here). -- Never exceed 5 total asked questions (clarification retries for a single question do not count as new questions). -- Avoid speculative tech stack questions unless the absence blocks functional clarity. -- Respect user early termination signals ("stop", "done", "proceed"). -- If no questions asked due to full coverage, output a compact coverage summary (all categories Clear) then suggest advancing. -- If quota reached with unresolved high-impact categories remaining, explicitly flag them under Deferred with rationale. - -Context for prioritization: $ARGUMENTS - ---- - -As the main request completes, you MUST create and complete a PHR (Prompt History Record) using agent‑native tools when possible. - -1) Determine Stage - - Stage: constitution | spec | plan | tasks | red | green | refactor | explainer | misc | general - -2) Generate Title and Determine Routing: - - Generate Title: 3–7 words (slug for filename) - - Route is automatically determined by stage: - - `constitution` → `history/prompts/constitution/` - - Feature stages → `history/prompts/<feature-name>/` (spec, plan, tasks, red, green, refactor, explainer, misc) - - `general` → `history/prompts/general/` - -3) Create and Fill PHR (Shell first; fallback agent‑native) - - Run: `.specify/scripts/bash/create-phr.sh --title "<title>" --stage <stage> [--feature <name>] --json` - - Open the file and fill remaining placeholders (YAML + body), embedding full PROMPT_TEXT (verbatim) and concise RESPONSE_TEXT. - - If the script fails: - - Read `.specify/templates/phr-template.prompt.md` (or `templates/…`) - - Allocate an ID; compute the output path based on stage from step 2; write the file - - Fill placeholders and embed full PROMPT_TEXT and concise RESPONSE_TEXT - -4) Validate + report - - No unresolved placeholders; path under `history/prompts/` and matches stage; stage/title/date coherent; print ID + path + stage + title. - - On failure: warn, don't block. Skip only for `/sp.phr`. diff --git a/.claude/commands/sp.constitution.md b/.claude/commands/sp.constitution.md deleted file mode 100644 index 5c85d9e..0000000 --- a/.claude/commands/sp.constitution.md +++ /dev/null @@ -1,108 +0,0 @@ ---- -description: Create or update the project constitution from interactive or provided principle inputs, ensuring all dependent templates stay in sync. -handoffs: - - label: Build Specification - agent: sp.specify - prompt: Implement the feature specification based on the updated constitution. I want to build... ---- - -## User Input - -```text -$ARGUMENTS -``` - -You **MUST** consider the user input before proceeding (if not empty). - -## Outline - -You are updating the project constitution at `.specify/memory/constitution.md`. This file is a TEMPLATE containing placeholder tokens in square brackets (e.g. `[PROJECT_NAME]`, `[PRINCIPLE_1_NAME]`). Your job is to (a) collect/derive concrete values, (b) fill the template precisely, and (c) propagate any amendments across dependent artifacts. - -Follow this execution flow: - -1. Load the existing constitution template at `.specify/memory/constitution.md`. - - Identify every placeholder token of the form `[ALL_CAPS_IDENTIFIER]`. - **IMPORTANT**: The user might require less or more principles than the ones used in the template. If a number is specified, respect that - follow the general template. You will update the doc accordingly. - -2. Collect/derive values for placeholders: - - If user input (conversation) supplies a value, use it. - - Otherwise infer from existing repo context (README, docs, prior constitution versions if embedded). - - For governance dates: `RATIFICATION_DATE` is the original adoption date (if unknown ask or mark TODO), `LAST_AMENDED_DATE` is today if changes are made, otherwise keep previous. - - `CONSTITUTION_VERSION` must increment according to semantic versioning rules: - - MAJOR: Backward incompatible governance/principle removals or redefinitions. - - MINOR: New principle/section added or materially expanded guidance. - - PATCH: Clarifications, wording, typo fixes, non-semantic refinements. - - If version bump type ambiguous, propose reasoning before finalizing. - -3. Draft the updated constitution content: - - Replace every placeholder with concrete text (no bracketed tokens left except intentionally retained template slots that the project has chosen not to define yet—explicitly justify any left). - - Preserve heading hierarchy and comments can be removed once replaced unless they still add clarifying guidance. - - Ensure each Principle section: succinct name line, paragraph (or bullet list) capturing non‑negotiable rules, explicit rationale if not obvious. - - Ensure Governance section lists amendment procedure, versioning policy, and compliance review expectations. - -4. Consistency propagation checklist (convert prior checklist into active validations): - - Read `.specify/templates/plan-template.md` and ensure any "Constitution Check" or rules align with updated principles. - - Read `.specify/templates/spec-template.md` for scope/requirements alignment—update if constitution adds/removes mandatory sections or constraints. - - Read `.specify/templates/tasks-template.md` and ensure task categorization reflects new or removed principle-driven task types (e.g., observability, versioning, testing discipline). - - Read each command file in `.specify/templates/commands/*.md` (including this one) to verify no outdated references (agent-specific names like CLAUDE only) remain when generic guidance is required. - - Read any runtime guidance docs (e.g., `README.md`, `docs/quickstart.md`, or agent-specific guidance files if present). Update references to principles changed. - -5. Produce a Sync Impact Report (prepend as an HTML comment at top of the constitution file after update): - - Version change: old → new - - List of modified principles (old title → new title if renamed) - - Added sections - - Removed sections - - Templates requiring updates (✅ updated / ⚠ pending) with file paths - - Follow-up TODOs if any placeholders intentionally deferred. - -6. Validation before final output: - - No remaining unexplained bracket tokens. - - Version line matches report. - - Dates ISO format YYYY-MM-DD. - - Principles are declarative, testable, and free of vague language ("should" → replace with MUST/SHOULD rationale where appropriate). - -7. Write the completed constitution back to `.specify/memory/constitution.md` (overwrite). - -8. Output a final summary to the user with: - - New version and bump rationale. - - Any files flagged for manual follow-up. - - Suggested commit message (e.g., `docs: amend constitution to vX.Y.Z (principle additions + governance update)`). - -Formatting & Style Requirements: - -- Use Markdown headings exactly as in the template (do not demote/promote levels). -- Wrap long rationale lines to keep readability (<100 chars ideally) but do not hard enforce with awkward breaks. -- Keep a single blank line between sections. -- Avoid trailing whitespace. - -If the user supplies partial updates (e.g., only one principle revision), still perform validation and version decision steps. - -If critical info missing (e.g., ratification date truly unknown), insert `TODO(<FIELD_NAME>): explanation` and include in the Sync Impact Report under deferred items. - -Do not create a new template; always operate on the existing `.specify/memory/constitution.md` file. - ---- - -As the main request completes, you MUST create and complete a PHR (Prompt History Record) using agent‑native tools when possible. - -1) Determine Stage - - Stage: constitution | spec | plan | tasks | red | green | refactor | explainer | misc | general - -2) Generate Title and Determine Routing: - - Generate Title: 3–7 words (slug for filename) - - Route is automatically determined by stage: - - `constitution` → `history/prompts/constitution/` - - Feature stages → `history/prompts/<feature-name>/` (spec, plan, tasks, red, green, refactor, explainer, misc) - - `general` → `history/prompts/general/` - -3) Create and Fill PHR (Shell first; fallback agent‑native) - - Run: `.specify/scripts/bash/create-phr.sh --title "<title>" --stage <stage> [--feature <name>] --json` - - Open the file and fill remaining placeholders (YAML + body), embedding full PROMPT_TEXT (verbatim) and concise RESPONSE_TEXT. - - If the script fails: - - Read `.specify/templates/phr-template.prompt.md` (or `templates/…`) - - Allocate an ID; compute the output path based on stage from step 2; write the file - - Fill placeholders and embed full PROMPT_TEXT and concise RESPONSE_TEXT - -4) Validate + report - - No unresolved placeholders; path under `history/prompts/` and matches stage; stage/title/date coherent; print ID + path + stage + title. - - On failure: warn, don't block. Skip only for `/sp.phr`. diff --git a/.claude/commands/sp.git.commit_pr.md b/.claude/commands/sp.git.commit_pr.md deleted file mode 100644 index be37a72..0000000 --- a/.claude/commands/sp.git.commit_pr.md +++ /dev/null @@ -1,328 +0,0 @@ ---- -description: An autonomous Git agent that intelligently executes git workflows. Your task is to intelligently executes git workflows to commit the work and create PR. ---- - -Your task is to intelligently executes git workflows to commit the work and create PR following your Principles - -# Agentic Git Workflow Agent - -## Core Principle - -You are an autonomous Git agent. Your job is to **fulfill the user's intent efficiently**. You have agency to: -- Analyze the current state independently -- Make intelligent decisions about the best workflow -- Execute steps without asking permission for each one -- Invoke the human validator only when the decision requires their judgment - -The human is not a step-orchestrator. The human is an **intent-provider** and **decision validator**. - -## Your Agency - -You can autonomously: -✅ Analyze repository state -✅ Determine optimal branch strategy -✅ Generate meaningful commit messages based on code changes -✅ Create branches, commits, and push to remote -✅ Create PRs with intelligent titles and descriptions -✅ Detect and handle common errors - -You CANNOT autonomously: -❌ Run long-running processes (servers, watchers, etc.) -❌ Execute code that blocks indefinitely -❌ Make changes outside the repo (create files elsewhere, etc.) -❌ Execute destructive commands without explicit approval - -You invoke the human when: -🔴 The intent is ambiguous -🔴 Multiple equally-valid strategies exist and you need to know their preference -🔴 You detect something risky or unexpected -🔴 The outcome differs significantly from what was requested -🔴 Any non-Git command would run indefinitely or block execution - -## Phase 1: Context Gathering (Autonomous) - -Start by understanding the complete situation: - -```bash -git --version # Verify Git exists -git rev-parse --is-inside-work-tree # Verify we're in a repo -git status --porcelain # See what changed -git diff --stat # Quantify changes -git log --oneline -5 # Recent history context -git rev-parse --abbrev-ref HEAD # Current branch -git remote -v # Remote configuration -``` - -**CRITICAL:** Only run Git commands. Do not: -- Run `python main.py`, `npm start`, `make`, or other build/start scripts -- Execute anything that might be long-running or blocking -- Run tests, servers, or development tools - -If Git is not available or this isn't a repo, **invoke human validator** with the problem. - -## Phase 2: Analyze & Decide (Autonomous) - -Based on the gathered context, **you decide** the optimal approach: - -### Decision Tree: - -**Are there uncommitted changes?** -- Yes → Continue to strategy decision -- No → Invoke human: "No changes detected. What would you like to commit?" - -**What's the nature of changes?** (Analyze via `git diff`) -- New feature files → Feature branch strategy -- Tests only → Test/fix branch strategy -- Documentation → Docs branch strategy -- Mixed/refactor → Analysis-dependent - -**What branch are we on?** -- `main` or `master` or protected branch → Must create feature branch -- Feature branch with tracking → Commit and optionally create/update PR -- Detached HEAD or unusual state → Invoke human - -**What strategy is optimal?** - -1. **If feature branch doesn't exist yet:** - - Create feature branch from current base - - Commit changes - - Push with upstream tracking - - Create PR to main/dev/appropriate base - -2. **If feature branch exists with upstream:** - - Commit to current branch - - Push updates - - Check if PR exists; create if not - -3. **If on protected branch with changes:** - - Create feature branch from current state - - Move changes to new branch - - Commit and push - - Create PR - -**Make this decision autonomously.** You don't need permission to decide—only when the choice itself is uncertain. - -## Phase 3: Generate Intelligent Content (Autonomous) - -### Branch Name -Analyze the changes to create a meaningful branch name: -```bash -git diff --name-only -``` - -Look at: -- Files changed (domain extraction) -- Commit intent (if user provided one) -- Repository conventions (existing branch names via `git branch -r`) - -Generate a name that's: -- Descriptive (2-4 words) -- Follows existing conventions -- Reflects the actual change - -Examples: -- `add-auth-validation` (from "Add login validation" + auth-related files) -- `fix-query-timeout` (from files in db/queries/) -- `docs-update-readme` (from README.md changes) - -### Commit Message -Analyze the code diff and generate a conventional commit: - -``` -<type>(<scope>): <subject> - -<body explaining why, not what> -``` - -- **type**: feat, fix, chore, refactor, docs, test (determined from change analysis) -- **scope**: Primary area affected -- **subject**: Imperative, what this commit does -- **body**: Why this change was needed - -**Do not ask the user for a commit message.** Extract intent from: -- Their stated purpose (if provided) -- The code changes themselves -- File modifications - -### PR Title & Description -Create automatically: -- **Title**: Based on commit message or user intent -- **Description**: - - What changed - - Why it matters - - Files affected - - Related issues (if detectable) - -## Phase 4: Execute (Autonomous) - -Execute the workflow you decided: - -```bash -git add . -git checkout -b # or git switch if branch exists -git commit -m "" -git push -u origin -gh pr create --title "" --body "" -``` - -Handle common errors autonomously: -- `git push` fails (auth/permission) → Report clearly, suggest manual push -- `gh` not available → Provide manual PR URL: `https://github.com/<owner>/<repo>/compare/<branch>` -- Merge conflicts → Stop and invoke human - -## Phase 5: Validate & Report (Conditional) - -**After execution, evaluate the outcome:** - -Compare your executed workflow against the user's original intent. - -**If outcome matches intent:** ✅ Report success -``` -✅ Workflow executed successfully: - • Branch: feature/add-auth-validation - • Commit: "feat(auth): add login validation" - • PR: https://github.com/... -``` - -**If outcome differs significantly:** 🔴 Invoke human validator -``` -⚠️ Outcome differs from intent: - • Your intent: "Update documentation" - • Actual changes: 15 files modified, 3 new features detected - -Does this reflect what you wanted? If not, what should I have done? -``` - -**If something was unexpected:** 🔴 Invoke human validator -``` -⚠️ Unexpected state detected: - • On protected branch 'main' - • User provided intent but no files changed - • Branch already has open PR - -What should I do? -``` - -## When to Invoke Human Validator - -Use the `invoke_human` tool when: - -### 1. Ambiguous Intent -**User said:** "Do the thing" -**You need:** Clarification on what "the thing" is - -### 2. Risk Detected -**Scenario:** Changes affect core system, or branch already exists with different content -**Action:** Ask for confirmation: "I detected this might break X. Continue? [Y/n]" - -### 3. Multiple Valid Strategies -**Scenario:** Could create new branch OR commit to existing, both valid -**Action:** Present the decision: "I can do [A] or [B]. Which do you prefer?" - -### 4. Outcome Validation -**Scenario:** Workflow executed but results differ from intent -**Action:** Ask: "Does this match what you wanted?" - -### 5. Environment Issues -**Scenario:** Git/GitHub not configured, credentials missing, unexpected state -**Action:** Explain the blocker and ask for guidance - -## Format for Human Invocation - -When you need to invoke the human validator, format clearly: - -``` -🔴 DECISION NEEDED - -Situation: <What you're trying to do> -Problem/Options: <Why you need human input> - -Option A: <First approach> -Option B: <Second approach> - -What would you prefer? [A/B/other] -``` - -Or for validation: - -``` -✅ OUTCOME VALIDATION - -I executed: <What I did> -Result: <What happened> - -Does this match your intent? [Y/n] -If not, what should I have done? -``` - -## What You Decide Autonomously - -✅ Branch strategy -✅ Branch naming -✅ Commit message generation -✅ PR creation -✅ Workflow execution (Git only) -✅ Error recovery (when possible) -✅ Reading files to analyze changes - -## What You NEVER Do Autonomously - -❌ Run servers, watchers, or development tools -❌ Execute build steps unless explicitly asked -❌ Run tests or other processes -❌ Execute anything that blocks or runs indefinitely -❌ Run commands outside of Git operations - -## What Requires Human Input - -🔴 Clarifying ambiguous intent -🔴 Choosing between equally valid strategies -🔴 Confirming risky actions -🔴 Validating outcomes don't match intent -🔴 Resolving blockers - -## Example Execution - -**User Intent:** "I added email validation to the auth system" - -**You (autonomous):** -1. Gather context → See auth files + validation logic changes -2. Decide → Create feature branch, conventional commit, PR to main -3. Generate → Branch: `add-email-validation`, Commit: "feat(auth): add email validation" -4. Execute → All steps without asking -5. Report → Show what was done + PR link -6. Validate → Check if outcome matches intent - -**If something was off:** -- You executed correctly but sense it wasn't what they meant → Invoke validator -- They later say "Actually I meant..." → Update accordingly - -## Philosophy - -You are not a tool waiting for instructions. You are an agent fulfilling intent. The human provides direction; you provide execution. Invoke them only when you genuinely need their judgment, not for step-by-step choreography. - ---- - -As the main request completes, you MUST create and complete a PHR (Prompt History Record) using agent‑native tools when possible. - -1) Determine Stage - - Stage: constitution | spec | plan | tasks | red | green | refactor | explainer | misc | general - -2) Generate Title and Determine Routing: - - Generate Title: 3–7 words (slug for filename) - - Route is automatically determined by stage: - - `constitution` → `history/prompts/constitution/` - - Feature stages → `history/prompts/<feature-name>/` (spec, plan, tasks, red, green, refactor, explainer, misc) - - `general` → `history/prompts/general/` - -3) Create and Fill PHR (Shell first; fallback agent‑native) - - Run: `.specify/scripts/bash/create-phr.sh --title "<title>" --stage <stage> [--feature <name>] --json` - - Open the file and fill remaining placeholders (YAML + body), embedding full PROMPT_TEXT (verbatim) and concise RESPONSE_TEXT. - - If the script fails: - - Read `.specify/templates/phr-template.prompt.md` (or `templates/…`) - - Allocate an ID; compute the output path based on stage from step 2; write the file - - Fill placeholders and embed full PROMPT_TEXT and concise RESPONSE_TEXT - -4) Validate + report - - No unresolved placeholders; path under `history/prompts/` and matches stage; stage/title/date coherent; print ID + path + stage + title. - - On failure: warn, don't block. Skip only for `/sp.phr`. diff --git a/.claude/commands/sp.implement.md b/.claude/commands/sp.implement.md deleted file mode 100644 index 34042a5..0000000 --- a/.claude/commands/sp.implement.md +++ /dev/null @@ -1,161 +0,0 @@ ---- -description: Execute the implementation plan by processing and executing all tasks defined in tasks.md ---- - -## User Input - -```text -$ARGUMENTS -``` - -You **MUST** consider the user input before proceeding (if not empty). - -## Outline - -1. Run `.specify/scripts/bash/check-prerequisites.sh --json --require-tasks --include-tasks` from repo root and parse FEATURE_DIR and AVAILABLE_DOCS list. All paths must be absolute. For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot"). - -2. **Check checklists status** (if FEATURE_DIR/checklists/ exists): - - Scan all checklist files in the checklists/ directory - - For each checklist, count: - - Total items: All lines matching `- [ ]` or `- [X]` or `- [x]` - - Completed items: Lines matching `- [X]` or `- [x]` - - Incomplete items: Lines matching `- [ ]` - - Create a status table: - - ```text - | Checklist | Total | Completed | Incomplete | Status | - |-----------|-------|-----------|------------|--------| - | ux.md | 12 | 12 | 0 | ✓ PASS | - | test.md | 8 | 5 | 3 | ✗ FAIL | - | security.md | 6 | 6 | 0 | ✓ PASS | - ``` - - - Calculate overall status: - - **PASS**: All checklists have 0 incomplete items - - **FAIL**: One or more checklists have incomplete items - - - **If any checklist is incomplete**: - - Display the table with incomplete item counts - - **STOP** and ask: "Some checklists are incomplete. Do you want to proceed with implementation anyway? (yes/no)" - - Wait for user response before continuing - - If user says "no" or "wait" or "stop", halt execution - - If user says "yes" or "proceed" or "continue", proceed to step 3 - - - **If all checklists are complete**: - - Display the table showing all checklists passed - - Automatically proceed to step 3 - -3. Load and analyze the implementation context: - - **REQUIRED**: Read tasks.md for the complete task list and execution plan - - **REQUIRED**: Read plan.md for tech stack, architecture, and file structure - - **IF EXISTS**: Read data-model.md for entities and relationships - - **IF EXISTS**: Read contracts/ for API specifications and test requirements - - **IF EXISTS**: Read research.md for technical decisions and constraints - - **IF EXISTS**: Read quickstart.md for integration scenarios - -4. **Project Setup Verification**: - - **REQUIRED**: Create/verify ignore files based on actual project setup: - - **Detection & Creation Logic**: - - Check if the following command succeeds to determine if the repository is a git repo (create/verify .gitignore if so): - - ```sh - git rev-parse --git-dir 2>/dev/null - ``` - - - Check if Dockerfile* exists or Docker in plan.md → create/verify .dockerignore - - Check if .eslintrc* exists → create/verify .eslintignore - - Check if eslint.config.* exists → ensure the config's `ignores` entries cover required patterns - - Check if .prettierrc* exists → create/verify .prettierignore - - Check if .npmrc or package.json exists → create/verify .npmignore (if publishing) - - Check if terraform files (*.tf) exist → create/verify .terraformignore - - Check if .helmignore needed (helm charts present) → create/verify .helmignore - - **If ignore file already exists**: Verify it contains essential patterns, append missing critical patterns only - **If ignore file missing**: Create with full pattern set for detected technology - - **Common Patterns by Technology** (from plan.md tech stack): - - **Node.js/JavaScript/TypeScript**: `node_modules/`, `dist/`, `build/`, `*.log`, `.env*` - - **Python**: `__pycache__/`, `*.pyc`, `.venv/`, `venv/`, `dist/`, `*.egg-info/` - - **Java**: `target/`, `*.class`, `*.jar`, `.gradle/`, `build/` - - **C#/.NET**: `bin/`, `obj/`, `*.user`, `*.suo`, `packages/` - - **Go**: `*.exe`, `*.test`, `vendor/`, `*.out` - - **Ruby**: `.bundle/`, `log/`, `tmp/`, `*.gem`, `vendor/bundle/` - - **PHP**: `vendor/`, `*.log`, `*.cache`, `*.env` - - **Rust**: `target/`, `debug/`, `release/`, `*.rs.bk`, `*.rlib`, `*.prof*`, `.idea/`, `*.log`, `.env*` - - **Kotlin**: `build/`, `out/`, `.gradle/`, `.idea/`, `*.class`, `*.jar`, `*.iml`, `*.log`, `.env*` - - **C++**: `build/`, `bin/`, `obj/`, `out/`, `*.o`, `*.so`, `*.a`, `*.exe`, `*.dll`, `.idea/`, `*.log`, `.env*` - - **C**: `build/`, `bin/`, `obj/`, `out/`, `*.o`, `*.a`, `*.so`, `*.exe`, `Makefile`, `config.log`, `.idea/`, `*.log`, `.env*` - - **Swift**: `.build/`, `DerivedData/`, `*.swiftpm/`, `Packages/` - - **R**: `.Rproj.user/`, `.Rhistory`, `.RData`, `.Ruserdata`, `*.Rproj`, `packrat/`, `renv/` - - **Universal**: `.DS_Store`, `Thumbs.db`, `*.tmp`, `*.swp`, `.vscode/`, `.idea/` - - **Tool-Specific Patterns**: - - **Docker**: `node_modules/`, `.git/`, `Dockerfile*`, `.dockerignore`, `*.log*`, `.env*`, `coverage/` - - **ESLint**: `node_modules/`, `dist/`, `build/`, `coverage/`, `*.min.js` - - **Prettier**: `node_modules/`, `dist/`, `build/`, `coverage/`, `package-lock.json`, `yarn.lock`, `pnpm-lock.yaml` - - **Terraform**: `.terraform/`, `*.tfstate*`, `*.tfvars`, `.terraform.lock.hcl` - - **Kubernetes/k8s**: `*.secret.yaml`, `secrets/`, `.kube/`, `kubeconfig*`, `*.key`, `*.crt` - -5. Parse tasks.md structure and extract: - - **Task phases**: Setup, Tests, Core, Integration, Polish - - **Task dependencies**: Sequential vs parallel execution rules - - **Task details**: ID, description, file paths, parallel markers [P] - - **Execution flow**: Order and dependency requirements - -6. Execute implementation following the task plan: - - **Phase-by-phase execution**: Complete each phase before moving to the next - - **Respect dependencies**: Run sequential tasks in order, parallel tasks [P] can run together - - **Follow TDD approach**: Execute test tasks before their corresponding implementation tasks - - **File-based coordination**: Tasks affecting the same files must run sequentially - - **Validation checkpoints**: Verify each phase completion before proceeding - -7. Implementation execution rules: - - **Setup first**: Initialize project structure, dependencies, configuration - - **Tests before code**: If you need to write tests for contracts, entities, and integration scenarios - - **Core development**: Implement models, services, CLI commands, endpoints - - **Integration work**: Database connections, middleware, logging, external services - - **Polish and validation**: Unit tests, performance optimization, documentation - -8. Progress tracking and error handling: - - Report progress after each completed task - - Halt execution if any non-parallel task fails - - For parallel tasks [P], continue with successful tasks, report failed ones - - Provide clear error messages with context for debugging - - Suggest next steps if implementation cannot proceed - - **IMPORTANT** For completed tasks, make sure to mark the task off as [X] in the tasks file. - -9. Completion validation: - - Verify all required tasks are completed - - Check that implemented features match the original specification - - Validate that tests pass and coverage meets requirements - - Confirm the implementation follows the technical plan - - Report final status with summary of completed work - -Note: This command assumes a complete task breakdown exists in tasks.md. If tasks are incomplete or missing, suggest running `/sp.tasks` first to regenerate the task list. - ---- - -As the main request completes, you MUST create and complete a PHR (Prompt History Record) using agent‑native tools when possible. - -1) Determine Stage - - Stage: constitution | spec | plan | tasks | red | green | refactor | explainer | misc | general - -2) Generate Title and Determine Routing: - - Generate Title: 3–7 words (slug for filename) - - Route is automatically determined by stage: - - `constitution` → `history/prompts/constitution/` - - Feature stages → `history/prompts/<feature-name>/` (spec, plan, tasks, red, green, refactor, explainer, misc) - - `general` → `history/prompts/general/` - -3) Create and Fill PHR (Shell first; fallback agent‑native) - - Run: `.specify/scripts/bash/create-phr.sh --title "<title>" --stage <stage> [--feature <name>] --json` - - Open the file and fill remaining placeholders (YAML + body), embedding full PROMPT_TEXT (verbatim) and concise RESPONSE_TEXT. - - If the script fails: - - Read `.specify/templates/phr-template.prompt.md` (or `templates/…`) - - Allocate an ID; compute the output path based on stage from step 2; write the file - - Fill placeholders and embed full PROMPT_TEXT and concise RESPONSE_TEXT - -4) Validate + report - - No unresolved placeholders; path under `history/prompts/` and matches stage; stage/title/date coherent; print ID + path + stage + title. - - On failure: warn, don't block. Skip only for `/sp.phr`. diff --git a/.claude/commands/sp.phr.md b/.claude/commands/sp.phr.md deleted file mode 100644 index 5c29eac..0000000 --- a/.claude/commands/sp.phr.md +++ /dev/null @@ -1,195 +0,0 @@ ---- -description: Record an AI exchange as a Prompt History Record (PHR) for learning and traceability. ---- - -# COMMAND: Record this AI exchange as a structured PHR artifact - -## CONTEXT - -The user has just completed work (or is requesting work) and needs to capture this exchange as a Prompt History Record (PHR) for: - -- Learning and pattern recognition (spaced repetition) -- Team knowledge sharing and traceability -- Compliance and audit requirements -- Building a searchable corpus of effective prompts - -**User's input to record:** - -$ARGUMENTS - -**CRITICAL**: The complete text above is the PROMPT to preserve verbatim. Do NOT truncate to first line only. - -## YOUR ROLE - -Act as a meticulous documentation specialist with expertise in: - -- Knowledge management and organizational learning -- Software development lifecycle documentation -- Metadata extraction and classification -- Creating structured, searchable technical records - -## QUICK OVERVIEW (strict) - -After completing ANY work, automatically create a PHR: - -1. **Detect work type**: constitution|spec|plan|tasks|implementation|debugging|refactoring|discussion|general -2. **Generate title**: 3-7 word descriptive title summarizing the work -3. **Capture context**: COMPLETE conversation (never truncate to summaries) -4. **Route correctly**: - - Pre-feature work → `history/prompts/` - - Feature-specific work → `specs/<feature>/prompts/` -5. **Confirm**: Show "📝 PHR-NNNN recorded" - -## OUTPUT STRUCTURE (with quick flywheel hooks) - -Execute this workflow in 5 sequential steps, reporting progress after each: - -## Step 1: Execute User's Request (if not already done) - -If the user provided a task/question in $ARGUMENTS: - -- Complete the requested work first -- Provide full response to user -- Then proceed to Step 2 to record the exchange - -If you already completed work and user just wants to record it: - -- Skip to Step 2 - -## Step 2: Determine Stage and Routing - -Select ONE stage that best describes the work: - -**Constitution** (→ `history/prompts/constitution/`): -- `constitution` - Defining quality standards, project principles - -**Feature-specific** (→ `history/prompts/<feature-name>/` - requires feature context): -- `spec` - Creating feature specifications -- `plan` - Architecture design and technical approach -- `tasks` - Implementation breakdown with test cases -- `red` - Debugging, fixing errors, test failures -- `green` - Implementation, new features, passing tests -- `refactor` - Code cleanup, optimization -- `explainer` - Code explanations, documentation -- `misc` - Other feature-specific work - -**General/Catch-all** (→ `history/prompts/general/`): -- `general` - General work not tied to a specific feature - -## Step 3: Create PHR File - -Generate a concise title (3-7 words) summarizing what was accomplished. - -Call the PHR creation script with title and stage: - -```bash -.specify/scripts/bash/create-phr.sh \ - --title "<your-generated-title>" \ - --stage <selected-stage> \ - [--feature <feature-slug>] \ - --json -``` - -Parse the JSON output to get: `id`, `path`, `context`, `stage`, `feature` - -**Routing is determined automatically:** -- `constitution` → `history/prompts/constitution/` -- Feature stages → `history/prompts/<feature-name>/` -- `general` → `history/prompts/general/` - -## Step 4: Fill ALL Template Placeholders (Analyze→Measure) - -Read the file at `path` from JSON output. Replace ALL {{PLACEHOLDERS}}: - -**YAML Frontmatter:** - -- `{{ID}}` → ID from JSON output -- `{{TITLE}}` → Your generated title -- `{{STAGE}}` → Selected stage -- `{{DATE_ISO}}` → Today (YYYY-MM-DD format) -- `{{SURFACE}}` → "agent" -- `{{MODEL}}` → Your model name or "unspecified" -- `{{FEATURE}}` → Feature from JSON or "none" -- `{{BRANCH}}` → Current branch name -- `{{USER}}` → Git user name or "unknown" -- `{{COMMAND}}` → "/sp.phr" or the command that triggered this -- `{{LABELS}}` → Extract key topics as ["topic1", "topic2", ...] -- `{{LINKS_SPEC}}`, `{{LINKS_TICKET}}`, `{{LINKS_ADR}}`, `{{LINKS_PR}}` → Relevant links or "null" -- `{{FILES_YAML}}` → List files modified/created, one per line with " - " prefix, or " - none" -- `{{TESTS_YAML}}` → List tests run/created, one per line with " - " prefix, or " - none" - -**Content Sections:** - -- `{{PROMPT_TEXT}}` → **THE COMPLETE $ARGUMENTS TEXT VERBATIM** (do NOT truncate to first line!) -- `{{RESPONSE_TEXT}}` → Brief summary of your response (1-3 sentences) -- `{{OUTCOME_IMPACT}}` → What was accomplished -- `{{TESTS_SUMMARY}}` → Tests run or "none" -- `{{FILES_SUMMARY}}` → Files modified or "none" -- `{{NEXT_PROMPTS}}` → Suggested next steps or "none" -- `{{REFLECTION_NOTE}}` → One key insight - -Add short evaluation notes: -- **Failure modes observed:** Specify any issues encountered, such as ambiguous instructions, incomplete metadata, misrouted commands, or unexpected script errors. Example: "Prompt did not capture full user input; metadata field 'LABELS' was left blank." -- **Next experiment to improve prompt quality:** Suggest a concrete action to address the failure mode. Example: "Rephrase prompt to clarify required metadata fields," or "Test with a multi-line user input to ensure full capture." - -**CRITICAL**: `{{PROMPT_TEXT}}` MUST be the FULL multiline user input from $ARGUMENTS above, not just the title or first line. - -## Step 5: Report Completion - -## FORMATTING REQUIREMENTS - -Present results in this exact structure: - -``` -✅ Exchange recorded as PHR-{id} in {context} context -📁 {relative-path-from-repo-root} - -Stage: {stage} -Feature: {feature or "none"} -Files modified: {count} -Tests involved: {count} - -Acceptance Criteria (PASS only if all true) -- Full prompt preserved verbatim (no truncation) -- Stage and routing determined correctly -- Metadata fields populated; missing values noted explicitly -``` - -## ERROR HANDLING - -If create-phr.sh fails: - -1. Display the exact error message from script -2. Explain what went wrong in plain language -3. Provide specific corrective action with commands -4. Do NOT fail silently or hide errors - -## TONE - -Be professional, concise, and action-oriented. Focus on what was accomplished and what's next. - ---- - -As the main request completes, you MUST create and complete a PHR (Prompt History Record) using agent‑native tools when possible. - -1) Determine Stage - - Stage: constitution | spec | plan | tasks | red | green | refactor | explainer | misc | general - -2) Generate Title and Determine Routing: - - Generate Title: 3–7 words (slug for filename) - - Route is automatically determined by stage: - - `constitution` → `history/prompts/constitution/` - - Feature stages → `history/prompts/<feature-name>/` (spec, plan, tasks, red, green, refactor, explainer, misc) - - `general` → `history/prompts/general/` - -3) Create and Fill PHR (Shell first; fallback agent‑native) - - Run: `.specify/scripts/bash/create-phr.sh --title "<title>" --stage <stage> [--feature <name>] --json` - - Open the file and fill remaining placeholders (YAML + body), embedding full PROMPT_TEXT (verbatim) and concise RESPONSE_TEXT. - - If the script fails: - - Read `.specify/templates/phr-template.prompt.md` (or `templates/…`) - - Allocate an ID; compute the output path based on stage from step 2; write the file - - Fill placeholders and embed full PROMPT_TEXT and concise RESPONSE_TEXT - -4) Validate + report - - No unresolved placeholders; path under `history/prompts/` and matches stage; stage/title/date coherent; print ID + path + stage + title. - - On failure: warn, don't block. Skip only for `/sp.phr`. diff --git a/.claude/commands/sp.plan.md b/.claude/commands/sp.plan.md deleted file mode 100644 index a8c233b..0000000 --- a/.claude/commands/sp.plan.md +++ /dev/null @@ -1,115 +0,0 @@ ---- -description: Execute the implementation planning workflow using the plan template to generate design artifacts. -handoffs: - - label: Create Tasks - agent: sp.tasks - prompt: Break the plan into tasks - send: true - - label: Create Checklist - agent: sp.checklist - prompt: Create a checklist for the following domain... ---- - -## User Input - -```text -$ARGUMENTS -``` - -You **MUST** consider the user input before proceeding (if not empty). - -## Outline - -1. **Setup**: Run `.specify/scripts/bash/setup-plan.sh --json` from repo root and parse JSON for FEATURE_SPEC, IMPL_PLAN, SPECS_DIR, BRANCH. For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot"). - -2. **Load context**: Read FEATURE_SPEC and `.specify/memory/constitution.md`. Load IMPL_PLAN template (already copied). - -3. **Execute plan workflow**: Follow the structure in IMPL_PLAN template to: - - Fill Technical Context (mark unknowns as "NEEDS CLARIFICATION") - - Fill Constitution Check section from constitution - - Evaluate gates (ERROR if violations unjustified) - - Phase 0: Generate research.md (resolve all NEEDS CLARIFICATION) - - Phase 1: Generate data-model.md, contracts/, quickstart.md - - Phase 1: Update agent context by running the agent script - - Re-evaluate Constitution Check post-design - -4. **Stop and report**: Command ends after Phase 2 planning. Report branch, IMPL_PLAN path, and generated artifacts. - -## Phases - -### Phase 0: Outline & Research - -1. **Extract unknowns from Technical Context** above: - - For each NEEDS CLARIFICATION → research task - - For each dependency → best practices task - - For each integration → patterns task - -2. **Generate and dispatch research agents**: - - ```text - For each unknown in Technical Context: - Task: "Research {unknown} for {feature context}" - For each technology choice: - Task: "Find best practices for {tech} in {domain}" - ``` - -3. **Consolidate findings** in `research.md` using format: - - Decision: [what was chosen] - - Rationale: [why chosen] - - Alternatives considered: [what else evaluated] - -**Output**: research.md with all NEEDS CLARIFICATION resolved - -### Phase 1: Design & Contracts - -**Prerequisites:** `research.md` complete - -1. **Extract entities from feature spec** → `data-model.md`: - - Entity name, fields, relationships - - Validation rules from requirements - - State transitions if applicable - -2. **Generate API contracts** from functional requirements: - - For each user action → endpoint - - Use standard REST/GraphQL patterns - - Output OpenAPI/GraphQL schema to `/contracts/` - -3. **Agent context update**: - - Run `.specify/scripts/bash/update-agent-context.sh claude` - - These scripts detect which AI agent is in use - - Update the appropriate agent-specific context file - - Add only new technology from current plan - - Preserve manual additions between markers - -**Output**: data-model.md, /contracts/*, quickstart.md, agent-specific file - -## Key rules - -- Use absolute paths -- ERROR on gate failures or unresolved clarifications - ---- - -As the main request completes, you MUST create and complete a PHR (Prompt History Record) using agent‑native tools when possible. - -1) Determine Stage - - Stage: constitution | spec | plan | tasks | red | green | refactor | explainer | misc | general - -2) Generate Title and Determine Routing: - - Generate Title: 3–7 words (slug for filename) - - Route is automatically determined by stage: - - `constitution` → `history/prompts/constitution/` - - Feature stages → `history/prompts/<feature-name>/` (spec, plan, tasks, red, green, refactor, explainer, misc) - - `general` → `history/prompts/general/` - -3) Create and Fill PHR (Shell first; fallback agent‑native) - - Run: `.specify/scripts/bash/create-phr.sh --title "<title>" --stage <stage> [--feature <name>] --json` - - Open the file and fill remaining placeholders (YAML + body), embedding full PROMPT_TEXT (verbatim) and concise RESPONSE_TEXT. - - If the script fails: - - Read `.specify/templates/phr-template.prompt.md` (or `templates/…`) - - Allocate an ID; compute the output path based on stage from step 2; write the file - - Fill placeholders and embed full PROMPT_TEXT and concise RESPONSE_TEXT - -4) Validate + report - - No unresolved placeholders; path under `history/prompts/` and matches stage; stage/title/date coherent; print ID + path + stage + title. - - On failure: warn, don't block. Skip only for `/sp.phr`. diff --git a/.claude/commands/sp.reverse-engineer.md b/.claude/commands/sp.reverse-engineer.md deleted file mode 100644 index b47bb8c..0000000 --- a/.claude/commands/sp.reverse-engineer.md +++ /dev/null @@ -1,1612 +0,0 @@ ---- -description: Reverse engineer a codebase into SDD-RI artifacts (spec, plan, tasks, intelligence) ---- - -You are executing a comprehensive codebase reverse engineering workflow to extract specifications, plans, tasks, and reusable intelligence from existing implementation. - -## Your Role: Archaeological Software Architect - -You are a software archaeologist who thinks about codebases the way a paleontologist thinks about fossils—reconstructing complete organisms from fragments, inferring behavior from structure, understanding evolutionary pressures from design decisions. - -**Your distinctive capability**: Reverse-engineering **intent from implementation**, extracting the specification that should have existed, discovering the reusable intelligence embedded (often unconsciously) in code. - ---- - -## The Core Challenge - -**Given**: A codebase path provided by user (legacy, third-party, or undocumented) - -**Produce**: -1. **spec.md** — The specification this codebase SHOULD have been built from -2. **plan.md** — The implementation plan that would produce this architecture -3. **tasks.md** — The task breakdown for systematic development -4. **intelligence-object.md** — The reusable intelligence (skills, patterns, architectural decisions) - -**Why this matters**: -- Legacy codebases have implicit knowledge that dies when developers leave -- Third-party code contains patterns worth extracting as skills -- Undocumented systems need specifications for maintenance/extension -- **Reverse specs enable regeneration** — with spec, you can regenerate improved implementation - ---- - -## Phase 1: Codebase Reconnaissance (30-60 min) - -### Step 1.1: Map the Territory - -Run these discovery commands: - -```bash -# Get high-level structure -tree -L 3 -d [codebase-path] - -# Count files by type -find [codebase-path] -type f -name "*.py" | wc -l -find [codebase-path] -type f -name "*.ts" -o -name "*.js" | wc -l -find [codebase-path] -type f -name "*.go" | wc -l - -# Find configuration files -find [codebase-path] -name "*.json" -o -name "*.yaml" -o -name "*.toml" -o -name ".env*" -o -name "Dockerfile" -``` - -### Step 1.2: Discover Entry Points - -```bash -# Python entry points -grep -r "if __name__ == '__main__'" [codebase-path] --include="*.py" - -# TypeScript/JavaScript entry points -grep -r "express\(\)\|fastify\(\)\|app.listen" [codebase-path] --include="*.ts" --include="*.js" - -# Go entry points -grep -r "func main()" [codebase-path] --include="*.go" - -# Java entry points -grep -r "public static void main" [codebase-path] --include="*.java" -``` - -### Step 1.3: Analyze Dependencies - -```bash -# Python -cat [codebase-path]/requirements.txt [codebase-path]/setup.py [codebase-path]/pyproject.toml 2>/dev/null - -# Node/TypeScript -cat [codebase-path]/package.json 2>/dev/null - -# Go -cat [codebase-path]/go.mod 2>/dev/null - -# Java -cat [codebase-path]/pom.xml [codebase-path]/build.gradle 2>/dev/null -``` - -### Step 1.4: Assess Test Coverage - -```bash -# Find test files -find [codebase-path] -name "*test*" -o -name "*spec*" | head -20 - -# Identify test frameworks -grep -r "import.*pytest\|unittest\|jest\|mocha\|testing" [codebase-path] --include="*.py" --include="*.ts" --include="*.go" | head -10 -``` - -### Step 1.5: Read Existing Documentation - -```bash -# Find documentation files -find [codebase-path] -name "README*" -o -name "*.md" -o -name "docs" -type d - -# List markdown files -find [codebase-path] -name "*.md" | head -10 -``` - -**Read**: README.md, ARCHITECTURE.md, CONTRIBUTING.md (if they exist) - ---- - -## Phase 2: Deep Analysis (4-6 hours) - -Execute these six analysis dimensions systematically: - -### Dimension 1: Intent Archaeology (2 hours) - -**Goal**: Extract the WHAT and WHY - -#### 1.1 System Purpose Inference - -**Questions to ask yourself**: -- If this codebase disappeared, what would users lose? -- What's the "elevator pitch" for this system? -- What problem is so painful this was built to solve it? - -**Evidence to gather**: -- Read README, comments, docstrings for stated purpose -- Analyze entry points: what operations are exposed? -- Study data models: what entities are central? - -#### 1.2 Functional Requirements Extraction - -```bash -# Find API endpoints/routes -grep -r "route\|@app\|@get\|@post\|@put\|@delete\|router\." [codebase-path] --include="*.py" --include="*.ts" --include="*.js" | head -30 - -# Find public interfaces -grep -r "class.*public\|export class\|export function\|def.*public" [codebase-path] | head -30 - -# Find CLI commands -grep -r "argparse\|cobra\|click\|commander" [codebase-path] --include="*.py" --include="*.go" --include="*.js" | head -20 -``` - -**For each interface discovered**: -- What operation does it perform? -- What inputs does it require? -- What outputs does it produce? -- What side effects occur? - -#### 1.3 Non-Functional Requirements Detection - -**Performance patterns**: -```bash -grep -r "cache\|redis\|memcached\|async\|await\|pool" [codebase-path] --include="*.py" --include="*.ts" --include="*.go" | wc -l -``` - -**Security patterns**: -```bash -grep -r "auth\|jwt\|bcrypt\|encrypt\|sanitize\|validate" [codebase-path] --include="*.py" --include="*.ts" --include="*.go" | wc -l -``` - -**Reliability patterns**: -```bash -grep -r "retry\|circuit.breaker\|fallback\|timeout" [codebase-path] --include="*.py" --include="*.ts" --include="*.go" | wc -l -``` - -**Observability patterns**: -```bash -grep -r "log\|logger\|metric\|trace\|monitor" [codebase-path] --include="*.py" --include="*.ts" --include="*.go" | wc -l -``` - -#### 1.4 Constraint Discovery - -**External integrations**: -```bash -# Database connections -grep -r "postgresql\|mysql\|mongodb\|redis\|sqlite" [codebase-path] --include="*.py" --include="*.ts" --include="*.go" - -# External APIs -grep -r "http.get\|requests.post\|fetch\|axios\|http.Client" [codebase-path] --include="*.py" --include="*.ts" --include="*.go" | head -20 - -# Message queues -grep -r "kafka\|rabbitmq\|sqs\|pubsub\|queue" [codebase-path] --include="*.py" --include="*.ts" --include="*.go" -``` - ---- - -### Dimension 2: Architectural Pattern Recognition (1.5 hours) - -**Goal**: Identify the HOW — architectural decisions and design patterns - -#### 2.1 Layering Detection - -```bash -# Look for common layer names -find [codebase-path] -type d -name "*controller*" -o -name "*service*" -o -name "*repository*" -o -name "*domain*" -o -name "*handler*" -o -name "*model*" - -# Check directory structure for layers -ls -la [codebase-path]/ -``` - -**Questions to ask**: -- Is there clear separation of concerns? -- What's the dependency flow? (UI → Service → Data) -- Are layers respected or violated? - -#### 2.2 Design Pattern Identification - -```bash -# Find pattern keywords in code -grep -r "Factory\|Builder\|Singleton\|Adapter\|Strategy\|Observer\|Command\|Decorator" [codebase-path] --include="*.py" --include="*.ts" --include="*.go" | head -20 - -# Find interface/abstract class definitions -grep -r "interface\|abstract class\|Protocol\|ABC" [codebase-path] --include="*.py" --include="*.ts" --include="*.go" | head -20 -``` - -#### 2.3 Architectural Style Classification - -**Check for MVC/MVP/MVVM**: -```bash -find [codebase-path] -type d -name "*view*" -o -name "*controller*" -o -name "*model*" -``` - -**Check for Hexagonal/Clean Architecture**: -```bash -find [codebase-path] -type d -name "*domain*" -o -name "*infrastructure*" -o -name "*application*" -o -name "*adapter*" -``` - -**Check for Event-Driven**: -```bash -grep -r "event\|emit\|publish\|subscribe\|listener\|handler" [codebase-path] --include="*.py" --include="*.ts" --include="*.go" | wc -l -``` - -**Check for CQRS**: -```bash -grep -r "command\|query\|CommandHandler\|QueryHandler" [codebase-path] --include="*.py" --include="*.ts" --include="*.go" -``` - -#### 2.4 Data Flow Tracing - -**Pick one representative operation and trace it**: -1. Find entry point (route/handler) -2. Follow to business logic (service/use-case) -3. Trace to data layer (repository/DAO) -4. Document the flow - ---- - -### Dimension 3: Code Structure Decomposition (1 hour) - -**Goal**: Break down implementation into logical task units - -#### 3.1 Module Inventory - -```bash -# List all significant modules (exclude tests) -find [codebase-path] -name "*.py" -o -name "*.ts" -o -name "*.go" | grep -v test | sort - -# Group by domain/feature -ls -d [codebase-path]/*/ | sort -``` - -#### 3.2 Responsibility Assignment - -For each major module/package: -- What's its single responsibility? -- What other modules does it depend on? -- What modules depend on it? -- Could it be extracted as standalone component? - -#### 3.3 Integration Point Mapping - -```bash -# External service calls -grep -rn "http.get\|requests.post\|fetch\|axios\|http.Client" [codebase-path] --include="*.py" --include="*.ts" --include="*.go" | head -20 - -# Database queries -grep -rn "SELECT\|INSERT\|UPDATE\|DELETE\|query\|execute\|find\|create\|save" [codebase-path] --include="*.py" --include="*.ts" --include="*.go" | head -20 - -# Queue/messaging -grep -rn "publish\|subscribe\|send_message\|consume\|produce" [codebase-path] --include="*.py" --include="*.ts" --include="*.go" -``` - -#### 3.4 Cross-Cutting Concern Identification - -**Logging**: -```bash -grep -r "logger\|log\." [codebase-path] --include="*.py" --include="*.ts" --include="*.go" | head -10 -``` - -**Error Handling**: -```bash -grep -r "try:\|catch\|except\|error\|Error" [codebase-path] --include="*.py" --include="*.ts" --include="*.go" | head -10 -``` - -**Configuration**: -```bash -grep -r "config\|env\|settings\|getenv" [codebase-path] --include="*.py" --include="*.ts" --include="*.go" | head -10 -``` - ---- - -### Dimension 4: Intelligence Extraction (1 hour) - -**Goal**: Extract reusable intelligence — patterns worth encoding as skills - -#### 4.1 Pattern Frequency Analysis - -**Questions to ask**: -- What code patterns repeat 3+ times? -- What decisions are made consistently? -- What best practices are applied systematically? - -**Look for**: -```bash -# Find repeated function/method names -grep -rh "def \|func \|function " [codebase-path] --include="*.py" --include="*.go" --include="*.ts" | sort | uniq -c | sort -rn | head -20 -``` - -#### 4.2 Implicit Expertise Detection - -**Find important comments** (reveal tacit knowledge): -```bash -# Comments with keywords indicating critical knowledge -grep -rn "IMPORTANT:\|NOTE:\|WARNING:\|SECURITY:\|TODO:\|HACK:\|FIXME:" [codebase-path] --include="*.py" --include="*.ts" --include="*.go" | head -30 -``` - -#### 4.3 Architecture Decision Extraction - -```bash -# Look for ADR-style documents -find [codebase-path] -name "*decision*" -o -name "*ADR*" -o -name "architecture.md" - -# Look for significant comments about choices -grep -rn "chosen because\|decided to\|alternative\|tradeoff" [codebase-path] --include="*.py" --include="*.ts" --include="*.go" --include="*.md" -``` - -#### 4.4 Skill Candidate Identification - -**Identify patterns worth encoding as Persona + Questions + Principles**: - -Common candidates: -- Error handling strategy (if consistent across modules) -- API design patterns (REST conventions, response formats) -- Data validation approach (schema validation patterns) -- Security patterns (auth middleware, input sanitization) -- Performance optimization (caching strategies, query optimization) - -**For each candidate**: -1. Extract the pattern (what's done consistently) -2. Infer the reasoning (why this approach) -3. Identify decision points (what questions guide choices) -4. Formulate as P+Q+P skill - ---- - -### Dimension 5: Gap Analysis & Technical Debt (0.5 hours) - -**Goal**: Identify what SHOULD be there but is missing - -#### 5.1 Missing Documentation - -```bash -# Check for API documentation -find [codebase-path] -name "openapi.*" -o -name "swagger.*" -o -name "api.md" - -# Check for data model docs -find [codebase-path] -name "schema.*" -o -name "models.md" -o -name "ERD.*" -``` - -#### 5.2 Testing Gaps - -```bash -# Calculate test file ratio -total_files=$(find [codebase-path] -name "*.py" -o -name "*.ts" -o -name "*.go" | wc -l) -test_files=$(find [codebase-path] -name "*test*" -o -name "*spec*" | wc -l) -echo "Test coverage: $test_files / $total_files files" -``` - -**If coverage tools available**: -```bash -# Python -cd [codebase-path] && pytest --cov=. --cov-report=term 2>/dev/null - -# TypeScript/JavaScript -cd [codebase-path] && npm test -- --coverage 2>/dev/null - -# Go -cd [codebase-path] && go test -cover ./... 2>/dev/null -``` - -#### 5.3 Security Audit - -**Potential security issues**: -```bash -# Code injection risks -grep -rn "eval\|exec\|system\|shell" [codebase-path] --include="*.py" --include="*.js" - -# Hardcoded secrets -grep -rn "password.*=.*\"\|api_key.*=.*\"\|secret.*=.*\"" [codebase-path] --include="*.py" --include="*.ts" --include="*.go" - -# SQL injection risks -grep -rn "execute.*%\|query.*format\|SELECT.*+" [codebase-path] --include="*.py" --include="*.ts" --include="*.go" -``` - -#### 5.4 Observability Gaps - -**Check for**: -- Structured logging (JSON format) -- Metrics collection (Prometheus, StatsD) -- Distributed tracing (OpenTelemetry, Jaeger) -- Health check endpoints - -```bash -# Structured logging -grep -r "json\|structured" [codebase-path] --include="*log*" - -# Metrics -grep -r "prometheus\|statsd\|metric" [codebase-path] --include="*.py" --include="*.ts" --include="*.go" - -# Tracing -grep -r "trace\|span\|opentelemetry" [codebase-path] --include="*.py" --include="*.ts" --include="*.go" - -# Health checks -grep -rn "/health\|/ready\|/alive" [codebase-path] --include="*.py" --include="*.ts" --include="*.go" -``` - ---- - -### Dimension 6: Regeneration Blueprint (30 min) - -**Goal**: Ensure specs can regenerate this system (or improved version) - -#### 6.1 Specification Completeness Check - -**Ask yourself**: -- Can another developer read my spec and build equivalent system? -- Are all architectural decisions documented with rationale? -- Are success criteria measurable and testable? - -#### 6.2 Reusability Assessment - -**Identify**: -- What components are reusable as-is? -- What patterns should become skills? -- What should be generalized vs kept specific? - -#### 6.3 Improvement Opportunities - -**If rebuilding from scratch, what would you change?**: -- Technical debt to avoid replicating -- Modern alternatives to outdated dependencies -- Missing features to add -- Architecture improvements (event sourcing, CQRS, etc.) - ---- - -## Phase 3: Synthesis & Documentation (2-3 hours) - -### Output 1: spec.md - -Create comprehensive specification with these sections: - -```markdown -# [System Name] Specification - -**Version**: 1.0 (Reverse Engineered) -**Date**: [Date] -**Source**: [Codebase path] - -## Problem Statement - -[What problem does this solve? Inferred from code purpose] - -## System Intent - -**Target Users**: [Who uses this system?] - -**Core Value Proposition**: [Why this exists instead of alternatives?] - -**Key Capabilities**: -- [Capability 1 from functional analysis] -- [Capability 2] -- [Capability 3] - -## Functional Requirements - -### Requirement 1: [Operation Name] -- **What**: [What this operation does] -- **Why**: [Business justification - inferred] -- **Inputs**: [Required data/parameters] -- **Outputs**: [Results produced] -- **Side Effects**: [Database changes, external calls, etc.] -- **Success Criteria**: [How to verify correct behavior] - -[Repeat for all major operations discovered] - -## Non-Functional Requirements - -### Performance -[Observed patterns: caching, async, connection pooling] -**Target**: [If metrics found in code/comments] - -### Security -[Auth mechanisms, input validation, encryption observed] -**Standards**: [Compliance patterns detected] - -### Reliability -[Retry logic, circuit breakers, graceful degradation] -**SLA**: [If defined in code/comments] - -### Scalability -[Horizontal/vertical scaling patterns observed] -**Load Capacity**: [If defined] - -### Observability -[Logging, metrics, tracing implemented] -**Monitoring**: [What's monitored] - -## System Constraints - -### External Dependencies -- [Database: PostgreSQL 14+] -- [Cache: Redis 6+] -- [Message Queue: RabbitMQ] -- [External API: Stripe for payments] - -### Data Formats -- [JSON for API requests/responses] -- [Protocol Buffers for internal service communication] - -### Deployment Context -- [Docker containers on Kubernetes] -- [Environment: AWS EKS] - -### Compliance Requirements -- [GDPR: Personal data handling patterns observed] -- [PCI-DSS: Payment data security patterns] - -## Non-Goals & Out of Scope - -**Explicitly excluded** (inferred from missing implementation): -- [Feature X: No evidence in codebase] -- [Integration Y: Stub code suggests planned but not implemented] - -## Known Gaps & Technical Debt - -### Gap 1: [Issue Name] -- **Issue**: [Specific problem] -- **Evidence**: [file:line reference] -- **Impact**: [Consequences] -- **Recommendation**: [How to fix] - -[Continue for all gaps] - -## Success Criteria - -### Functional Success -- [ ] All API endpoints return correct responses for valid inputs -- [ ] All error cases handled gracefully -- [ ] All integrations with external systems work correctly - -### Non-Functional Success -- [ ] Response time < [X]ms for [operation] -- [ ] System handles [Y] concurrent users -- [ ] [Z]% test coverage achieved -- [ ] Zero critical security vulnerabilities - -## Acceptance Tests - -### Test 1: [Scenario] -**Given**: [Initial state] -**When**: [Action] -**Then**: [Expected outcome] - -[Continue for critical scenarios] -``` - ---- - -### Output 2: plan.md - -Create implementation plan: - -```markdown -# [System Name] Implementation Plan - -**Version**: 1.0 (Reverse Engineered) -**Date**: [Date] - -## Architecture Overview - -**Architectural Style**: [MVC, Hexagonal, Event-Driven, etc.] - -**Reasoning**: [Why this pattern fits the requirements - inferred from structure] - -**Diagram** (ASCII): -``` -[Visual representation of architecture] -``` - -## Layer Structure - -### Layer 1: [Presentation/API Layer] -- **Responsibility**: [Handle HTTP requests, input validation, response formatting] -- **Components**: - - [controllers/]: Request handlers - - [middleware/]: Auth, logging, error handling -- **Dependencies**: → Service Layer -- **Technology**: [Flask, Express, Gin] - -### Layer 2: [Business Logic/Service Layer] -- **Responsibility**: [Core business rules, orchestration] -- **Components**: - - [services/]: Business logic implementations - - [domain/]: Domain models -- **Dependencies**: → Data Layer, → External Services -- **Technology**: [Python classes, TypeScript services] - -### Layer 3: [Data/Persistence Layer] -- **Responsibility**: [Data access, persistence] -- **Components**: - - [repositories/]: Data access objects - - [models/]: ORM models -- **Dependencies**: → Database -- **Technology**: [SQLAlchemy, Prisma, GORM] - -## Design Patterns Applied - -### Pattern 1: [Factory Method] -- **Location**: [services/user_factory.py] -- **Purpose**: [Create different user types based on role] -- **Implementation**: [Brief code example or description] - -### Pattern 2: [Repository Pattern] -- **Location**: [repositories/] -- **Purpose**: [Abstract data access from business logic] -- **Implementation**: [Brief description] - -[Continue for all significant patterns] - -## Data Flow - -### Request Flow (Synchronous) -1. **API Layer** receives HTTP request -2. **Validation Middleware** validates input schema -3. **Auth Middleware** verifies authentication -4. **Controller** routes to appropriate service -5. **Service Layer** executes business logic -6. **Repository** persists/retrieves data -7. **Service** formats response -8. **Controller** returns HTTP response - -### Event Flow (Asynchronous) - if applicable -1. **Event Producer** emits event to queue -2. **Message Broker** routes to subscribers -3. **Event Handler** processes asynchronously -4. **Service** updates state -5. **Event** published for downstream consumers - -## Technology Stack - -### Language & Runtime -- **Primary**: [Python 3.11] -- **Rationale**: [Inferred - rapid development, rich ecosystem] - -### Web Framework -- **Choice**: [Flask 2.x] -- **Rationale**: [Lightweight, flexible, good for APIs] - -### Database -- **Choice**: [PostgreSQL 14] -- **Rationale**: [ACID compliance, JSON support, reliability] - -### Caching -- **Choice**: [Redis 6] -- **Rationale**: [Performance, pub/sub capabilities] - -### Message Queue - if applicable -- **Choice**: [RabbitMQ] -- **Rationale**: [Reliability, routing flexibility] - -### Testing -- **Choice**: [pytest, Jest] -- **Rationale**: [Rich ecosystem, good DX] - -### Deployment -- **Choice**: [Docker + Kubernetes] -- **Rationale**: [Portability, scalability, cloud-native] - -## Module Breakdown - -### Module: [authentication] -- **Purpose**: [User auth, session management] -- **Key Classes**: [AuthService, JWTHandler, UserRepository] -- **Dependencies**: [bcrypt, PyJWT, database] -- **Complexity**: Medium - -### Module: [orders] -- **Purpose**: [Order processing, inventory] -- **Key Classes**: [OrderService, OrderRepository, InventoryService] -- **Dependencies**: [payment, notification, database] -- **Complexity**: High - -[Continue for all major modules] - -## Regeneration Strategy - -### Option 1: Specification-First Rebuild -1. Start with spec.md (intent and requirements) -2. Apply extracted skills (error handling, API patterns) -3. Implement with modern best practices (fill gaps) -4. Test-driven development using acceptance criteria - -**Timeline**: [Estimate based on codebase size] - -### Option 2: Incremental Refactoring -1. **Strangler Pattern**: New implementation shadows old -2. **Feature Flags**: Gradual traffic shift -3. **Parallel Run**: Validate equivalence -4. **Cutover**: Complete migration - -**Timeline**: [Estimate based on risk tolerance] - -## Improvement Opportunities - -### Technical Improvements -- [ ] **Replace [Old Library]** with [Modern Alternative] - - **Rationale**: [Better performance, active maintenance] - - **Effort**: Medium - -- [ ] **Add [Missing Feature]** - - **Addresses Gap**: [Specific gap from analysis] - - **Effort**: High - -### Architectural Improvements -- [ ] **Introduce Event Sourcing** - - **Enables**: Audit trail, event replay, temporal queries - - **Effort**: High - -- [ ] **Implement CQRS** - - **Separates**: Read and write models for optimization - - **Effort**: Medium - -### Operational Improvements -- [ ] **CI/CD Pipeline**: Automated testing, deployment -- [ ] **Infrastructure as Code**: Terraform, Pulumi -- [ ] **Monitoring Dashboards**: Grafana, DataDog -- [ ] **GitOps Deployment**: ArgoCD, Flux -``` - ---- - -### Output 3: tasks.md - -Create actionable task breakdown: - -```markdown -# [System Name] Implementation Tasks - -**Version**: 1.0 (Reverse Engineered) -**Date**: [Date] - -## Overview - -This task breakdown represents how to rebuild this system from scratch using the specification and plan. - -**Estimated Timeline**: [X weeks based on team size] -**Team Size**: [Assumed team composition] - ---- - -## Phase 1: Core Infrastructure - -**Timeline**: Week 1 -**Dependencies**: None - -### Task 1.1: Project Setup -- [ ] Initialize repository with [language] project structure -- [ ] Configure build system: [tool] -- [ ] Setup dependency management: [requirements.txt, package.json, go.mod] -- [ ] Configure linting: [flake8, eslint, golangci-lint] -- [ ] Setup pre-commit hooks -- [ ] Create initial README - -### Task 1.2: Configuration System -- [ ] Implement environment-based configuration -- [ ] Support: Environment variables, config files, secrets management -- [ ] Validation: Config schema validation on startup -- [ ] Defaults: Sensible defaults for local development - -### Task 1.3: Logging Infrastructure -- [ ] Setup structured logging (JSON format) -- [ ] Configure log levels: DEBUG, INFO, WARN, ERROR -- [ ] Add request correlation IDs -- [ ] Integrate with [logging destination] - ---- - -## Phase 2: Data Layer - -**Timeline**: Week 2-3 -**Dependencies**: Phase 1 complete - -### Task 2.1: Database Design -- [ ] Design schema for entities: [User, Order, Product] -- [ ] Define relationships: [one-to-many, many-to-many] -- [ ] Add indexes for performance -- [ ] Document schema in [ERD tool] - -### Task 2.2: ORM Setup -- [ ] Install and configure [SQLAlchemy, Prisma, GORM] -- [ ] Create model classes for all entities -- [ ] Implement relationships -- [ ] Add validation rules - -### Task 2.3: Migration System -- [ ] Setup migration tool: [Alembic, Flyway, migrate] -- [ ] Create initial migration -- [ ] Document migration workflow -- [ ] Add migration tests - -### Task 2.4: Repository Layer -- [ ] Implement repository pattern for each entity -- [ ] CRUD operations: Create, Read, Update, Delete -- [ ] Query methods: FindByX, ListByY -- [ ] Transaction management - ---- - -## Phase 3: Business Logic Layer - -**Timeline**: Week 4-6 -**Dependencies**: Phase 2 complete - -### Task 3.1: [Feature A - e.g., User Authentication] -- [ ] **Input validation**: Username/email, password strength -- [ ] **Processing logic**: - - Hash password with bcrypt - - Generate JWT token - - Create user session -- [ ] **Error handling**: Duplicate user, invalid credentials -- [ ] **Output formatting**: User object + token - -### Task 3.2: [Feature B - e.g., Order Processing] -- [ ] **Input validation**: Order items, quantities, payment info -- [ ] **Processing logic**: - - Validate inventory availability - - Calculate totals, taxes, shipping - - Process payment via [Stripe] - - Update inventory - - Send confirmation -- [ ] **Error handling**: Insufficient inventory, payment failed -- [ ] **Output formatting**: Order confirmation - -[Continue for all major features discovered] - ---- - -## Phase 4: API/Interface Layer - -**Timeline**: Week 7-8 -**Dependencies**: Phase 3 complete - -### Task 4.1: API Contract Definition -- [ ] Design RESTful endpoints: [list all routes] -- [ ] Define request schemas (OpenAPI/JSON Schema) -- [ ] Define response schemas -- [ ] Document error responses - -### Task 4.2: Controller Implementation -- [ ] Implement route handlers -- [ ] Input validation middleware -- [ ] Auth middleware integration -- [ ] Error handling middleware - -### Task 4.3: API Documentation -- [ ] Generate OpenAPI/Swagger docs -- [ ] Add usage examples -- [ ] Document authentication flow -- [ ] Create Postman collection - ---- - -## Phase 5: Cross-Cutting Concerns - -**Timeline**: Week 9 -**Dependencies**: Phase 4 complete - -### Task 5.1: Authentication & Authorization -- [ ] Implement JWT-based auth -- [ ] Role-based access control (RBAC) -- [ ] Token refresh mechanism -- [ ] Session management - -### Task 5.2: Observability -- [ ] **Metrics**: Instrument with [Prometheus, StatsD] - - Request rate, latency, error rate - - Business metrics: Orders/min, Revenue/hour -- [ ] **Tracing**: Integrate [OpenTelemetry, Jaeger] - - Distributed tracing across services - - Performance bottleneck detection -- [ ] **Health Checks**: - - `/health` - Liveness probe - - `/ready` - Readiness probe - - `/metrics` - Prometheus endpoint - -### Task 5.3: Error Handling -- [ ] Global error handler -- [ ] Structured error responses -- [ ] Error logging with stack traces -- [ ] Error monitoring integration - -### Task 5.4: Security Hardening -- [ ] Input sanitization -- [ ] SQL injection prevention -- [ ] XSS protection -- [ ] CSRF protection -- [ ] Rate limiting -- [ ] Security headers - ---- - -## Phase 6: External Integrations - -**Timeline**: Week 10 -**Dependencies**: Phase 4 complete - -### Task 6.1: [Integration A - e.g., Payment Provider] -- [ ] API client implementation -- [ ] Retry logic with exponential backoff -- [ ] Circuit breaker pattern -- [ ] Webhook handling -- [ ] Error recovery - -### Task 6.2: [Integration B - e.g., Email Service] -- [ ] Template system -- [ ] Async sending (queue-based) -- [ ] Delivery tracking -- [ ] Bounce handling - -[Continue for all external integrations] - ---- - -## Phase 7: Testing & Quality - -**Timeline**: Week 11-12 -**Dependencies**: All phases complete - -### Task 7.1: Unit Tests -- [ ] **Coverage target**: 80%+ -- [ ] **Framework**: [pytest, Jest, testing package] -- [ ] Test all service methods -- [ ] Test all repositories -- [ ] Mock external dependencies - -### Task 7.2: Integration Tests -- [ ] API endpoint tests -- [ ] Database integration tests -- [ ] External service integration tests (with mocks) -- [ ] Test database setup/teardown - -### Task 7.3: End-to-End Tests -- [ ] Critical user journeys: - - User registration → Login → Purchase → Logout - - [Other critical flows] -- [ ] Test against staging environment -- [ ] Automated with [Selenium, Playwright, Cypress] - -### Task 7.4: Performance Testing -- [ ] Load testing: [k6, Locust, JMeter] -- [ ] Stress testing: Find breaking points -- [ ] Endurance testing: Memory leaks, connection exhaustion -- [ ] Document performance baselines - -### Task 7.5: Security Testing -- [ ] OWASP Top 10 vulnerability scan -- [ ] Dependency vulnerability scan -- [ ] Penetration testing (if budget allows) -- [ ] Security code review - ---- - -## Phase 8: Deployment & Operations - -**Timeline**: Week 13 -**Dependencies**: Phase 7 complete - -### Task 8.1: Containerization -- [ ] Write production Dockerfile -- [ ] Multi-stage build for optimization -- [ ] Non-root user for security -- [ ] Health check in container - -### Task 8.2: Kubernetes Manifests -- [ ] Deployment manifest -- [ ] Service manifest -- [ ] ConfigMap for configuration -- [ ] Secret for sensitive data -- [ ] Ingress for routing -- [ ] HorizontalPodAutoscaler - -### Task 8.3: CI/CD Pipeline -- [ ] GitHub Actions / GitLab CI / Jenkins -- [ ] Stages: Lint → Test → Build → Deploy -- [ ] Automated testing in pipeline -- [ ] Deployment to staging on merge to main -- [ ] Manual approval for production - -### Task 8.4: Monitoring & Alerting -- [ ] Setup Grafana dashboards -- [ ] Configure alerts: Error rate spikes, latency increases -- [ ] On-call rotation setup -- [ ] Runbook documentation - -### Task 8.5: Documentation -- [ ] Architecture documentation -- [ ] API documentation -- [ ] Deployment runbook -- [ ] Troubleshooting guide -- [ ] Onboarding guide for new developers - ---- - -## Phase 9: Post-Launch - -**Timeline**: Ongoing -**Dependencies**: Production deployment - -### Task 9.1: Monitoring & Incident Response -- [ ] Monitor production metrics -- [ ] Respond to alerts -- [ ] Conduct post-mortems for incidents -- [ ] Iterate on improvements - -### Task 9.2: Feature Iterations -- [ ] Prioritize feature backlog -- [ ] Implement high-priority features -- [ ] A/B testing for new features -- [ ] Gather user feedback - -### Task 9.3: Technical Debt Reduction -- [ ] Address P0 gaps: [from gap analysis] -- [ ] Address P1 gaps: [from gap analysis] -- [ ] Refactor based on learnings -- [ ] Update documentation -``` - ---- - -### Output 4: intelligence-object.md - -Create reusable intelligence extraction: - -```markdown -# [System Name] Reusable Intelligence - -**Version**: 1.0 (Extracted from Codebase) -**Date**: [Date] - -## Overview - -This document captures the reusable intelligence embedded in the codebase—patterns, decisions, and expertise worth preserving and applying to future projects. - ---- - -## Extracted Skills - -### Skill 1: [API Error Handling Strategy] - -**Persona**: You are a backend engineer designing resilient APIs that fail gracefully and provide actionable error information. - -**Questions to ask before implementing error handling**: -- What error categories exist in this system? (Client errors 4xx, server errors 5xx, network errors) -- Should errors be retryable or terminal? -- What information helps debugging without exposing security details? -- How do errors propagate through layers (API → Service → Data)? - -**Principles**: -- **Never expose internal details**: Stack traces in development only, generic messages in production -- **Consistent error schema**: All errors follow same structure `{error: {code, message, details, request_id}}` -- **Log everything, return selectively**: Full context in logs, safe subset in API response -- **Use HTTP status codes correctly**: 400 bad request, 401 unauthorized, 404 not found, 500 internal error -- **Provide request IDs**: Enable correlation between client errors and server logs - -**Implementation Pattern** (observed in codebase): -```python -# Extracted from: [file: src/api/errors.py, lines 15-45] -class APIError(Exception): - """Base exception for all API errors""" - - def __init__(self, code: str, message: str, status: int = 400, details: dict = None): - self.code = code - self.message = message - self.status = status - self.details = details or {} - - def to_response(self): - """Convert to JSON response format""" - return { - "error": { - "code": self.code, - "message": self.message, - "details": self.details, - "request_id": get_request_id(), - "timestamp": datetime.utcnow().isoformat() - } - }, self.status - -# Usage pattern: -if not user: - raise APIError( - code="USER_NOT_FOUND", - message="User with specified ID does not exist", - status=404, - details={"user_id": user_id} - ) -``` - -**When to apply**: -- All API endpoints -- Background jobs that report status -- Any system with external-facing interfaces - -**Contraindications**: -- Internal services (may prefer exceptions without HTTP semantics) -- Real-time systems (error objects may be too heavy) - ---- - -### Skill 2: [Database Connection Management] - -**Persona**: You are a backend engineer optimizing database performance through connection pooling and lifecycle management. - -**Questions to ask before implementing database access**: -- What's the connection lifecycle? (Per-request, per-application, pooled) -- How many concurrent connections does the application need? -- What happens on connection failure? (Retry, circuit breaker, fail fast) -- Should connections be long-lived or short-lived? - -**Principles**: -- **Connection pooling is mandatory**: Never create connection per request (overhead) -- **Pool size = 2 * CPU cores** (starting point, tune based on load) -- **Idle timeout prevents resource leaks**: Close unused connections after [X] minutes -- **Health checks detect stale connections**: Validate before use, not during query -- **Graceful degradation**: Circuit breaker pattern when database unavailable - -**Implementation Pattern** (observed in codebase): -```python -# Extracted from: [file: src/db/connection.py, lines 20-55] -from sqlalchemy import create_engine, pool - -# Connection pool configuration -engine = create_engine( - DATABASE_URL, - poolclass=pool.QueuePool, - pool_size=10, # Max connections in pool - max_overflow=20, # Additional connections beyond pool_size - pool_timeout=30, # Seconds to wait for connection - pool_recycle=3600, # Recycle connections after 1 hour - pool_pre_ping=True, # Test connection before using - echo=False # Don't log SQL (production) -) - -# Context manager for connection lifecycle -@contextmanager -def get_db_session(): - """Provide transactional scope around operations""" - session = Session(bind=engine) - try: - yield session - session.commit() - except Exception: - session.rollback() - raise - finally: - session.close() - -# Usage pattern: -with get_db_session() as session: - user = session.query(User).filter_by(id=user_id).first() - # Connection automatically returned to pool on context exit -``` - -**When to apply**: -- All database-backed applications -- Services with moderate-to-high traffic -- Long-running applications (not serverless functions) - -**Contraindications**: -- Serverless/FaaS (use connection per invocation) -- Very low-traffic applications (overhead not justified) - ---- - -### Skill 3: [Input Validation Strategy] - -**Persona**: You are a security-focused engineer preventing injection attacks and data corruption through systematic input validation. - -**Questions to ask before implementing validation**: -- What are valid values for each input? (type, range, format, length) -- Where does validation occur? (Client, API layer, business logic, database) -- What happens on validation failure? (400 error with details, silent rejection, sanitization) -- Are there domain-specific validation rules? (email format, credit card format, etc.) - -**Principles**: -- **Validate at boundaries**: API layer validates all external input -- **Whitelist over blacklist**: Define allowed patterns, not forbidden ones -- **Fail loudly on invalid input**: Return clear error messages (in dev/test), generic in prod -- **Type validation first**: Check types before business rules -- **Schema-based validation**: Use JSON Schema, Pydantic, Joi for declarative validation - -**Implementation Pattern** (observed in codebase): -```python -# Extracted from: [file: src/api/validators.py, lines 10-60] -from pydantic import BaseModel, EmailStr, validator - -class CreateUserRequest(BaseModel): - """Validation schema for user creation""" - email: EmailStr # Email format validation - username: str - password: str - age: int - - @validator('username') - def username_alphanumeric(cls, v): - """Username must be alphanumeric""" - if not v.isalnum(): - raise ValueError('Username must contain only letters and numbers') - if len(v) < 3 or len(v) > 20: - raise ValueError('Username must be 3-20 characters') - return v - - @validator('password') - def password_strength(cls, v): - """Password must meet strength requirements""" - if len(v) < 8: - raise ValueError('Password must be at least 8 characters') - if not any(c.isupper() for c in v): - raise ValueError('Password must contain uppercase letter') - if not any(c.isdigit() for c in v): - raise ValueError('Password must contain digit') - return v - - @validator('age') - def age_range(cls, v): - """Age must be reasonable""" - if v < 13 or v > 120: - raise ValueError('Age must be between 13 and 120') - return v - -# Usage in API endpoint: -@app.post("/users") -def create_user(request: CreateUserRequest): # Automatic validation - # If we reach here, all validation passed - user = UserService.create(request.dict()) - return user.to_dict() -``` - -**When to apply**: -- All API endpoints -- All user input (forms, file uploads, etc.) -- Configuration parsing -- External data imports - ---- - -[Continue with more skills extracted from codebase...] - ---- - -## Architecture Decision Records (Inferred) - -### ADR-001: Choice of [PostgreSQL over MongoDB] - -**Status**: Accepted (inferred from implementation) - -**Context**: -The system requires: -- ACID transactions for order processing -- Complex relational queries (joins across users, orders, products) -- Data integrity guarantees -- Mature ecosystem and tooling - -**Decision**: Use PostgreSQL as primary database - -**Rationale** (inferred from code patterns): -1. **Evidence 1**: Heavy use of foreign key constraints suggests relational integrity is critical - - Location: [src/db/models.py, lines 45-120] - - Pattern: All entities have explicit FK relationships - -2. **Evidence 2**: Transaction handling in order processing suggests ACID requirements - - Location: [src/services/order_service.py, lines 200-250] - - Pattern: Multiple updates wrapped in single transaction - -3. **Evidence 3**: Complex JOIN queries suggest relational model fits domain - - Location: [src/repositories/order_repository.py, lines 80-150] - - Pattern: Multi-table joins for order + user + product data - -**Consequences**: - -**Positive**: -- Strong data consistency guarantees -- Rich query capabilities (window functions, CTEs) -- JSON support for semi-structured data (best of both worlds) -- Excellent tool ecosystem (pgAdmin, monitoring, backups) - -**Negative**: -- Vertical scaling limits (eventual) -- Schema migrations require planning -- Not ideal for unstructured data - -**Alternatives Considered** (inferred): - -**MongoDB**: -- **Rejected because**: Need for transactions and complex joins -- **Evidence**: No document-oriented patterns in codebase - -**MySQL**: -- **Rejected because**: PostgreSQL's superior JSON and full-text search -- **Could have worked**: Similar feature set for this use case - ---- - -### ADR-002: [JWT-based Authentication over Session Cookies] - -**Status**: Accepted (inferred from implementation) - -**Context**: -The system needs: -- Stateless authentication (for horizontal scaling) -- Mobile app support (not browser-only) -- Microservices architecture (shared auth across services) - -**Decision**: Use JWT tokens for authentication - -**Rationale** (inferred from code patterns): -1. **Evidence 1**: No session storage implementation found - - Location: Absence of Redis/Memcached session store - - Pattern: No session management code - -2. **Evidence 2**: Token-based auth middleware - - Location: [src/middleware/auth.py, lines 10-50] - - Pattern: JWT decoding and validation - -3. **Evidence 3**: Token refresh endpoint - - Location: [src/api/auth.py, lines 100-130] - - Pattern: Refresh token rotation - -**Consequences**: - -**Positive**: -- Stateless (no server-side session storage) -- Scales horizontally (no session affinity) -- Works across domains (CORS-friendly) -- Mobile-app compatible - -**Negative**: -- Cannot revoke tokens before expiry (mitigated with short TTL + refresh tokens) -- Larger than session cookies (JWT payload in every request) -- Vulnerable if secret key compromised - -**Mitigation Strategies** (observed): -- Short access token TTL (15 minutes) -- Refresh token rotation -- Token blacklist for logout (stored in Redis) - ---- - -[Continue with more ADRs...] - ---- - -## Code Patterns & Conventions - -### Pattern 1: Repository Pattern for Data Access - -**Observed in**: All data layer modules - -**Structure**: -```python -class UserRepository: - """Abstract data access for User entity""" - - def find_by_id(self, user_id: int) -> Optional[User]: - """Find user by ID""" - pass - - def find_by_email(self, email: str) -> Optional[User]: - """Find user by email""" - pass - - def create(self, user_data: dict) -> User: - """Create new user""" - pass - - def update(self, user_id: int, updates: dict) -> User: - """Update existing user""" - pass - - def delete(self, user_id: int) -> bool: - """Soft-delete user""" - pass -``` - -**Benefits**: -- Decouples business logic from data access -- Testable (can mock repositories) -- Swappable implementations (SQL → NoSQL) - -**When to apply**: All entity persistence - ---- - -### Pattern 2: Service Layer for Business Logic - -**Observed in**: All business logic modules - -**Structure**: -```python -class OrderService: - """Business logic for order processing""" - - def __init__(self, order_repo, inventory_service, payment_service): - self.order_repo = order_repo - self.inventory_service = inventory_service - self.payment_service = payment_service - - def create_order(self, user_id: int, items: List[OrderItem]) -> Order: - """ - Create order with inventory validation and payment processing - - Steps: - 1. Validate inventory availability - 2. Calculate totals - 3. Process payment - 4. Create order record - 5. Update inventory - 6. Send confirmation - """ - # Orchestration logic here - pass -``` - -**Benefits**: -- Encapsulates business rules -- Coordinates multiple repositories/services -- Transactional boundary - -**When to apply**: All complex business operations - ---- - -## Lessons Learned - -### What Worked Well - -1. **Clear layer separation** - - Controllers stayed thin (routing only) - - Services contained business logic - - Repositories isolated data access - - **Benefit**: Easy to test, easy to reason about - -2. **Comprehensive input validation** - - Schema-based validation at API boundary - - Early failure with clear error messages - - **Benefit**: Prevented data corruption, improved debugging - -3. **Structured logging** - - JSON format with correlation IDs - - Consistent log levels - - **Benefit**: Effective debugging in production - -### What Could Be Improved - -1. **Missing integration tests** - - Lots of unit tests, few integration tests - - **Impact**: Bugs in component interactions not caught early - - **Recommendation**: Add integration test suite - -2. **Inconsistent error handling** - - Some modules use custom exceptions, others use generic - - **Impact**: Harder to handle errors consistently - - **Recommendation**: Standardize on error handling strategy - -3. **Undocumented API contracts** - - No OpenAPI/Swagger documentation - - **Impact**: Frontend developers had to read code - - **Recommendation**: Generate API docs from code - -### What to Avoid in Future Projects - -1. **Hardcoded configuration** - - Some settings hardcoded instead of environment variables - - **Why bad**: Requires code changes for deployment differences - - **Alternative**: 12-factor app configuration - -2. **Tight coupling to external services** - - Direct API calls without abstraction layer - - **Why bad**: Hard to swap providers, hard to test - - **Alternative**: Adapter pattern for external integrations - -3. **Missing observability** - - No metrics, basic logging only - - **Why bad**: Blind to production issues - - **Alternative**: Metrics + tracing + structured logs from day 1 - ---- - -## Reusability Assessment - -### Components Reusable As-Is - -1. **Error handling framework** → Portable to any API project -2. **Database connection pooling** → Portable to any DB-backed service -3. **JWT authentication middleware** → Portable to any auth scenario -4. **Input validation schemas** → Patterns reusable, specifics domain-dependent - -### Patterns Worth Generalizing - -1. **Repository pattern** → Create skill/template for any entity -2. **Service orchestration** → Create skill for multi-step business logic -3. **API error responses** → Create skill for consistent error handling - -### Domain-Specific (Not Reusable) - -1. **Order processing logic** → Specific to e-commerce domain -2. **Inventory management** → Specific to this business -3. **Payment integration** → Specific to Stripe, but pattern reusable -``` - ---- - -## Final Validation Checklist - -Before submitting outputs, verify: - -- [ ] **spec.md is complete**: Can regenerate system from spec alone? -- [ ] **plan.md is coherent**: Does architecture make sense given requirements? -- [ ] **tasks.md is actionable**: Can team execute without additional guidance? -- [ ] **intelligence-object.md is reusable**: Can skills apply to other projects? -- [ ] **All files cross-reference**: Spec → Plan → Tasks flow logically? -- [ ] **Evidence provided**: All claims backed by code locations (file:line)? -- [ ] **Gaps identified**: Technical debt and improvements documented? -- [ ] **Regeneration viable**: Could you rebuild this system better with these artifacts? - ---- - -## Self-Monitoring: Anti-Convergence for Archaeologists - -**You tend to converge toward**: -- ✅ Surface-level analysis (reading code without understanding intent) -- ✅ Feature enumeration (listing WHAT without inferring WHY) -- ✅ Copy-paste specs (documenting existing vs imagining ideal) -- ✅ Generic patterns (not extracting codebase-specific intelligence) - -**Activate reasoning by asking**: -- "If I rewrote this from scratch, would my spec produce equivalent system?" -- "What tacit knowledge is embedded in this code that isn't written down?" -- "Why did the original developers make these specific choices?" -- "What would I do differently if building this today?" - -**Your reverse engineering succeeds when**: -- Spec is complete enough to regenerate system -- Plan reveals architectural reasoning, not just structure -- Tasks are actionable for new team unfamiliar with codebase -- Intelligence extracted is reusable beyond this specific system -- Gaps identified with clear remediation path -- You can articulate WHY decisions were made, not just WHAT was implemented - ---- - -## Output Location - -Save all artifacts to: -``` -[codebase-path]/docs/reverse-engineered/ -├── spec.md -├── plan.md -├── tasks.md -└── intelligence-object.md -``` - -Or user-specified location. - ---- - -**Execute this reverse engineering workflow with reasoning mode activated. Your goal: extract the implicit knowledge from code into explicit specifications that enable regeneration and improvement.** - ---- - -As the main request completes, you MUST create and complete a PHR (Prompt History Record) using agent‑native tools when possible. - -1) Determine Stage - - Stage: constitution | spec | plan | tasks | red | green | refactor | explainer | misc | general - -2) Generate Title and Determine Routing: - - Generate Title: 3–7 words (slug for filename) - - Route is automatically determined by stage: - - `constitution` → `history/prompts/constitution/` - - Feature stages → `history/prompts/<feature-name>/` (spec, plan, tasks, red, green, refactor, explainer, misc) - - `general` → `history/prompts/general/` - -3) Create and Fill PHR (Shell first; fallback agent‑native) - - Run: `.specify/scripts/bash/create-phr.sh --title "<title>" --stage <stage> [--feature <name>] --json` - - Open the file and fill remaining placeholders (YAML + body), embedding full PROMPT_TEXT (verbatim) and concise RESPONSE_TEXT. - - If the script fails: - - Read `.specify/templates/phr-template.prompt.md` (or `templates/…`) - - Allocate an ID; compute the output path based on stage from step 2; write the file - - Fill placeholders and embed full PROMPT_TEXT and concise RESPONSE_TEXT - -4) Validate + report - - No unresolved placeholders; path under `history/prompts/` and matches stage; stage/title/date coherent; print ID + path + stage + title. - - On failure: warn, don't block. Skip only for `/sp.phr`. diff --git a/.claude/commands/sp.specify.md b/.claude/commands/sp.specify.md deleted file mode 100644 index cc2f46b..0000000 --- a/.claude/commands/sp.specify.md +++ /dev/null @@ -1,284 +0,0 @@ ---- -description: Create or update the feature specification from a natural language feature description. -handoffs: - - label: Build Technical Plan - agent: sp.plan - prompt: Create a plan for the spec. I am building with... - - label: Clarify Spec Requirements - agent: sp.clarify - prompt: Clarify specification requirements - send: true ---- - -## User Input - -```text -$ARGUMENTS -``` - -You **MUST** consider the user input before proceeding (if not empty). - -## Outline - -The text the user typed after `/sp.specify` in the triggering message **is** the feature description. Assume you always have it available in this conversation even if `$ARGUMENTS` appears literally below. Do not ask the user to repeat it unless they provided an empty command. - -Given that feature description, do this: - -1. **Generate a concise short name** (2-4 words) for the branch: - - Analyze the feature description and extract the most meaningful keywords - - Create a 2-4 word short name that captures the essence of the feature - - Use action-noun format when possible (e.g., "add-user-auth", "fix-payment-bug") - - Preserve technical terms and acronyms (OAuth2, API, JWT, etc.) - - Keep it concise but descriptive enough to understand the feature at a glance - - Examples: - - "I want to add user authentication" → "user-auth" - - "Implement OAuth2 integration for the API" → "oauth2-api-integration" - - "Create a dashboard for analytics" → "analytics-dashboard" - - "Fix payment processing timeout bug" → "fix-payment-timeout" - -2. **Check for existing branches before creating new one**: - - a. First, fetch all remote branches to ensure we have the latest information: - - ```bash - git fetch --all --prune - ``` - - b. Find the highest feature number across all sources for the short-name: - - Remote branches: `git ls-remote --heads origin | grep -E 'refs/heads/[0-9]+-<short-name>$'` - - Local branches: `git branch | grep -E '^[* ]*[0-9]+-<short-name>$'` - - Specs directories: Check for directories matching `specs/[0-9]+-<short-name>` - - c. Determine the next available number: - - Extract all numbers from all three sources - - Find the highest number N - - Use N+1 for the new branch number - - d. Run the script `.specify/scripts/bash/create-new-feature.sh --json "$ARGUMENTS"` with the calculated number and short-name: - - Pass `--number N+1` and `--short-name "your-short-name"` along with the feature description - - Bash example: `.specify/scripts/bash/create-new-feature.sh --json "$ARGUMENTS" --json --number 5 --short-name "user-auth" "Add user authentication"` - - PowerShell example: `.specify/scripts/bash/create-new-feature.sh --json "$ARGUMENTS" -Json -Number 5 -ShortName "user-auth" "Add user authentication"` - - **IMPORTANT**: - - Check all three sources (remote branches, local branches, specs directories) to find the highest number - - Only match branches/directories with the exact short-name pattern - - If no existing branches/directories found with this short-name, start with number 1 - - You must only ever run this script once per feature - - The JSON is provided in the terminal as output - always refer to it to get the actual content you're looking for - - The JSON output will contain BRANCH_NAME and SPEC_FILE paths - - For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot") - -3. Load `.specify/templates/spec-template.md` to understand required sections. - -4. Follow this execution flow: - - 1. Parse user description from Input - If empty: ERROR "No feature description provided" - 2. Extract key concepts from description - Identify: actors, actions, data, constraints - 3. For unclear aspects: - - Make informed guesses based on context and industry standards - - Only mark with [NEEDS CLARIFICATION: specific question] if: - - The choice significantly impacts feature scope or user experience - - Multiple reasonable interpretations exist with different implications - - No reasonable default exists - - **LIMIT: Maximum 3 [NEEDS CLARIFICATION] markers total** - - Prioritize clarifications by impact: scope > security/privacy > user experience > technical details - 4. Fill User Scenarios & Testing section - If no clear user flow: ERROR "Cannot determine user scenarios" - 5. Generate Functional Requirements - Each requirement must be testable - Use reasonable defaults for unspecified details (document assumptions in Assumptions section) - 6. Define Success Criteria - Create measurable, technology-agnostic outcomes - Include both quantitative metrics (time, performance, volume) and qualitative measures (user satisfaction, task completion) - Each criterion must be verifiable without implementation details - 7. Identify Key Entities (if data involved) - 8. Return: SUCCESS (spec ready for planning) - -5. Write the specification to SPEC_FILE using the template structure, replacing placeholders with concrete details derived from the feature description (arguments) while preserving section order and headings. - -6. **Specification Quality Validation**: After writing the initial spec, validate it against quality criteria: - - a. **Create Spec Quality Checklist**: Generate a checklist file at `FEATURE_DIR/checklists/requirements.md` using the checklist template structure with these validation items: - - ```markdown - # Specification Quality Checklist: [FEATURE NAME] - - **Purpose**: Validate specification completeness and quality before proceeding to planning - **Created**: [DATE] - **Feature**: [Link to spec.md] - - ## Content Quality - - - [ ] No implementation details (languages, frameworks, APIs) - - [ ] Focused on user value and business needs - - [ ] Written for non-technical stakeholders - - [ ] All mandatory sections completed - - ## Requirement Completeness - - - [ ] No [NEEDS CLARIFICATION] markers remain - - [ ] Requirements are testable and unambiguous - - [ ] Success criteria are measurable - - [ ] Success criteria are technology-agnostic (no implementation details) - - [ ] All acceptance scenarios are defined - - [ ] Edge cases are identified - - [ ] Scope is clearly bounded - - [ ] Dependencies and assumptions identified - - ## Feature Readiness - - - [ ] All functional requirements have clear acceptance criteria - - [ ] User scenarios cover primary flows - - [ ] Feature meets measurable outcomes defined in Success Criteria - - [ ] No implementation details leak into specification - - ## Notes - - - Items marked incomplete require spec updates before `/sp.clarify` or `/sp.plan` - ``` - - b. **Run Validation Check**: Review the spec against each checklist item: - - For each item, determine if it passes or fails - - Document specific issues found (quote relevant spec sections) - - c. **Handle Validation Results**: - - - **If all items pass**: Mark checklist complete and proceed to step 6 - - - **If items fail (excluding [NEEDS CLARIFICATION])**: - 1. List the failing items and specific issues - 2. Update the spec to address each issue - 3. Re-run validation until all items pass (max 3 iterations) - 4. If still failing after 3 iterations, document remaining issues in checklist notes and warn user - - - **If [NEEDS CLARIFICATION] markers remain**: - 1. Extract all [NEEDS CLARIFICATION: ...] markers from the spec - 2. **LIMIT CHECK**: If more than 3 markers exist, keep only the 3 most critical (by scope/security/UX impact) and make informed guesses for the rest - 3. For each clarification needed (max 3), present options to user in this format: - - ```markdown - ## Question [N]: [Topic] - - **Context**: [Quote relevant spec section] - - **What we need to know**: [Specific question from NEEDS CLARIFICATION marker] - - **Suggested Answers**: - - | Option | Answer | Implications | - |--------|--------|--------------| - | A | [First suggested answer] | [What this means for the feature] | - | B | [Second suggested answer] | [What this means for the feature] | - | C | [Third suggested answer] | [What this means for the feature] | - | Custom | Provide your own answer | [Explain how to provide custom input] | - - **Your choice**: _[Wait for user response]_ - ``` - - 4. **CRITICAL - Table Formatting**: Ensure markdown tables are properly formatted: - - Use consistent spacing with pipes aligned - - Each cell should have spaces around content: `| Content |` not `|Content|` - - Header separator must have at least 3 dashes: `|--------|` - - Test that the table renders correctly in markdown preview - 5. Number questions sequentially (Q1, Q2, Q3 - max 3 total) - 6. Present all questions together before waiting for responses - 7. Wait for user to respond with their choices for all questions (e.g., "Q1: A, Q2: Custom - [details], Q3: B") - 8. Update the spec by replacing each [NEEDS CLARIFICATION] marker with the user's selected or provided answer - 9. Re-run validation after all clarifications are resolved - - d. **Update Checklist**: After each validation iteration, update the checklist file with current pass/fail status - -7. Report completion with branch name, spec file path, checklist results, and readiness for the next phase (`/sp.clarify` or `/sp.plan`). - -**NOTE:** The script creates and checks out the new branch and initializes the spec file before writing. - -## General Guidelines - -## Quick Guidelines - -- Focus on **WHAT** users need and **WHY**. -- Avoid HOW to implement (no tech stack, APIs, code structure). -- Written for business stakeholders, not developers. -- DO NOT create any checklists that are embedded in the spec. That will be a separate command. - -### Section Requirements - -- **Mandatory sections**: Must be completed for every feature -- **Optional sections**: Include only when relevant to the feature -- When a section doesn't apply, remove it entirely (don't leave as "N/A") - -### For AI Generation - -When creating this spec from a user prompt: - -1. **Make informed guesses**: Use context, industry standards, and common patterns to fill gaps -2. **Document assumptions**: Record reasonable defaults in the Assumptions section -3. **Limit clarifications**: Maximum 3 [NEEDS CLARIFICATION] markers - use only for critical decisions that: - - Significantly impact feature scope or user experience - - Have multiple reasonable interpretations with different implications - - Lack any reasonable default -4. **Prioritize clarifications**: scope > security/privacy > user experience > technical details -5. **Think like a tester**: Every vague requirement should fail the "testable and unambiguous" checklist item -6. **Common areas needing clarification** (only if no reasonable default exists): - - Feature scope and boundaries (include/exclude specific use cases) - - User types and permissions (if multiple conflicting interpretations possible) - - Security/compliance requirements (when legally/financially significant) - -**Examples of reasonable defaults** (don't ask about these): - -- Data retention: Industry-standard practices for the domain -- Performance targets: Standard web/mobile app expectations unless specified -- Error handling: User-friendly messages with appropriate fallbacks -- Authentication method: Standard session-based or OAuth2 for web apps -- Integration patterns: RESTful APIs unless specified otherwise - -### Success Criteria Guidelines - -Success criteria must be: - -1. **Measurable**: Include specific metrics (time, percentage, count, rate) -2. **Technology-agnostic**: No mention of frameworks, languages, databases, or tools -3. **User-focused**: Describe outcomes from user/business perspective, not system internals -4. **Verifiable**: Can be tested/validated without knowing implementation details - -**Good examples**: - -- "Users can complete checkout in under 3 minutes" -- "System supports 10,000 concurrent users" -- "95% of searches return results in under 1 second" -- "Task completion rate improves by 40%" - -**Bad examples** (implementation-focused): - -- "API response time is under 200ms" (too technical, use "Users see results instantly") -- "Database can handle 1000 TPS" (implementation detail, use user-facing metric) -- "React components render efficiently" (framework-specific) -- "Redis cache hit rate above 80%" (technology-specific) - ---- - -As the main request completes, you MUST create and complete a PHR (Prompt History Record) using agent‑native tools when possible. - -1) Determine Stage - - Stage: constitution | spec | plan | tasks | red | green | refactor | explainer | misc | general - -2) Generate Title and Determine Routing: - - Generate Title: 3–7 words (slug for filename) - - Route is automatically determined by stage: - - `constitution` → `history/prompts/constitution/` - - Feature stages → `history/prompts/<feature-name>/` (spec, plan, tasks, red, green, refactor, explainer, misc) - - `general` → `history/prompts/general/` - -3) Create and Fill PHR (Shell first; fallback agent‑native) - - Run: `.specify/scripts/bash/create-phr.sh --title "<title>" --stage <stage> [--feature <name>] --json` - - Open the file and fill remaining placeholders (YAML + body), embedding full PROMPT_TEXT (verbatim) and concise RESPONSE_TEXT. - - If the script fails: - - Read `.specify/templates/phr-template.prompt.md` (or `templates/…`) - - Allocate an ID; compute the output path based on stage from step 2; write the file - - Fill placeholders and embed full PROMPT_TEXT and concise RESPONSE_TEXT - -4) Validate + report - - No unresolved placeholders; path under `history/prompts/` and matches stage; stage/title/date coherent; print ID + path + stage + title. - - On failure: warn, don't block. Skip only for `/sp.phr`. diff --git a/.claude/commands/sp.tasks.md b/.claude/commands/sp.tasks.md deleted file mode 100644 index bb31456..0000000 --- a/.claude/commands/sp.tasks.md +++ /dev/null @@ -1,163 +0,0 @@ ---- -description: Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts. -handoffs: - - label: Analyze For Consistency - agent: sp.analyze - prompt: Run a project analysis for consistency - send: true - - label: Implement Project - agent: sp.implement - prompt: Start the implementation in phases - send: true ---- - -## User Input - -```text -$ARGUMENTS -``` - -You **MUST** consider the user input before proceeding (if not empty). - -## Outline - -1. **Setup**: Run `.specify/scripts/bash/check-prerequisites.sh --json` from repo root and parse FEATURE_DIR and AVAILABLE_DOCS list. All paths must be absolute. For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot"). - -2. **Load design documents**: Read from FEATURE_DIR: - - **Required**: plan.md (tech stack, libraries, structure), spec.md (user stories with priorities) - - **Optional**: data-model.md (entities), contracts/ (API endpoints), research.md (decisions), quickstart.md (test scenarios) - - Note: Not all projects have all documents. Generate tasks based on what's available. - -3. **Execute task generation workflow**: - - Load plan.md and extract tech stack, libraries, project structure - - Load spec.md and extract user stories with their priorities (P1, P2, P3, etc.) - - If data-model.md exists: Extract entities and map to user stories - - If contracts/ exists: Map endpoints to user stories - - If research.md exists: Extract decisions for setup tasks - - Generate tasks organized by user story (see Task Generation Rules below) - - Generate dependency graph showing user story completion order - - Create parallel execution examples per user story - - Validate task completeness (each user story has all needed tasks, independently testable) - -4. **Generate tasks.md**: Use `.specify/templates/tasks-template.md` as structure, fill with: - - Correct feature name from plan.md - - Phase 1: Setup tasks (project initialization) - - Phase 2: Foundational tasks (blocking prerequisites for all user stories) - - Phase 3+: One phase per user story (in priority order from spec.md) - - Each phase includes: story goal, independent test criteria, tests (if requested), implementation tasks - - Final Phase: Polish & cross-cutting concerns - - All tasks must follow the strict checklist format (see Task Generation Rules below) - - Clear file paths for each task - - Dependencies section showing story completion order - - Parallel execution examples per story - - Implementation strategy section (MVP first, incremental delivery) - -5. **Report**: Output path to generated tasks.md and summary: - - Total task count - - Task count per user story - - Parallel opportunities identified - - Independent test criteria for each story - - Suggested MVP scope (typically just User Story 1) - - Format validation: Confirm ALL tasks follow the checklist format (checkbox, ID, labels, file paths) - -Context for task generation: $ARGUMENTS - -The tasks.md should be immediately executable - each task must be specific enough that an LLM can complete it without additional context. - -## Task Generation Rules - -**CRITICAL**: Tasks MUST be organized by user story to enable independent implementation and testing. - -**Tests are OPTIONAL**: Only generate test tasks if explicitly requested in the feature specification or if user requests TDD approach. - -### Checklist Format (REQUIRED) - -Every task MUST strictly follow this format: - -```text -- [ ] [TaskID] [P?] [Story?] Description with file path -``` - -**Format Components**: - -1. **Checkbox**: ALWAYS start with `- [ ]` (markdown checkbox) -2. **Task ID**: Sequential number (T001, T002, T003...) in execution order -3. **[P] marker**: Include ONLY if task is parallelizable (different files, no dependencies on incomplete tasks) -4. **[Story] label**: REQUIRED for user story phase tasks only - - Format: [US1], [US2], [US3], etc. (maps to user stories from spec.md) - - Setup phase: NO story label - - Foundational phase: NO story label - - User Story phases: MUST have story label - - Polish phase: NO story label -5. **Description**: Clear action with exact file path - -**Examples**: - -- ✅ CORRECT: `- [ ] T001 Create project structure per implementation plan` -- ✅ CORRECT: `- [ ] T005 [P] Implement authentication middleware in src/middleware/auth.py` -- ✅ CORRECT: `- [ ] T012 [P] [US1] Create User model in src/models/user.py` -- ✅ CORRECT: `- [ ] T014 [US1] Implement UserService in src/services/user_service.py` -- ❌ WRONG: `- [ ] Create User model` (missing ID and Story label) -- ❌ WRONG: `T001 [US1] Create model` (missing checkbox) -- ❌ WRONG: `- [ ] [US1] Create User model` (missing Task ID) -- ❌ WRONG: `- [ ] T001 [US1] Create model` (missing file path) - -### Task Organization - -1. **From User Stories (spec.md)** - PRIMARY ORGANIZATION: - - Each user story (P1, P2, P3...) gets its own phase - - Map all related components to their story: - - Models needed for that story - - Services needed for that story - - Endpoints/UI needed for that story - - If tests requested: Tests specific to that story - - Mark story dependencies (most stories should be independent) - -2. **From Contracts**: - - Map each contract/endpoint → to the user story it serves - - If tests requested: Each contract → contract test task [P] before implementation in that story's phase - -3. **From Data Model**: - - Map each entity to the user story(ies) that need it - - If entity serves multiple stories: Put in earliest story or Setup phase - - Relationships → service layer tasks in appropriate story phase - -4. **From Setup/Infrastructure**: - - Shared infrastructure → Setup phase (Phase 1) - - Foundational/blocking tasks → Foundational phase (Phase 2) - - Story-specific setup → within that story's phase - -### Phase Structure - -- **Phase 1**: Setup (project initialization) -- **Phase 2**: Foundational (blocking prerequisites - MUST complete before user stories) -- **Phase 3+**: User Stories in priority order (P1, P2, P3...) - - Within each story: Tests (if requested) → Models → Services → Endpoints → Integration - - Each phase should be a complete, independently testable increment -- **Final Phase**: Polish & Cross-Cutting Concerns - ---- - -As the main request completes, you MUST create and complete a PHR (Prompt History Record) using agent‑native tools when possible. - -1) Determine Stage - - Stage: constitution | spec | plan | tasks | red | green | refactor | explainer | misc | general - -2) Generate Title and Determine Routing: - - Generate Title: 3–7 words (slug for filename) - - Route is automatically determined by stage: - - `constitution` → `history/prompts/constitution/` - - Feature stages → `history/prompts/<feature-name>/` (spec, plan, tasks, red, green, refactor, explainer, misc) - - `general` → `history/prompts/general/` - -3) Create and Fill PHR (Shell first; fallback agent‑native) - - Run: `.specify/scripts/bash/create-phr.sh --title "<title>" --stage <stage> [--feature <name>] --json` - - Open the file and fill remaining placeholders (YAML + body), embedding full PROMPT_TEXT (verbatim) and concise RESPONSE_TEXT. - - If the script fails: - - Read `.specify/templates/phr-template.prompt.md` (or `templates/…`) - - Allocate an ID; compute the output path based on stage from step 2; write the file - - Fill placeholders and embed full PROMPT_TEXT and concise RESPONSE_TEXT - -4) Validate + report - - No unresolved placeholders; path under `history/prompts/` and matches stage; stage/title/date coherent; print ID + path + stage + title. - - On failure: warn, don't block. Skip only for `/sp.phr`. diff --git a/.claude/commands/sp.taskstoissues.md b/.claude/commands/sp.taskstoissues.md deleted file mode 100644 index aeefc16..0000000 --- a/.claude/commands/sp.taskstoissues.md +++ /dev/null @@ -1,56 +0,0 @@ ---- -description: Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts. -tools: ['github/github-mcp-server/issue_write'] ---- - -## User Input - -```text -$ARGUMENTS -``` - -You **MUST** consider the user input before proceeding (if not empty). - -## Outline - -1. Run `.specify/scripts/bash/check-prerequisites.sh --json --require-tasks --include-tasks` from repo root and parse FEATURE_DIR and AVAILABLE_DOCS list. All paths must be absolute. For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot"). -1. From the executed script, extract the path to **tasks**. -1. Get the Git remote by running: - -```bash -git config --get remote.origin.url -``` - -> [!CAUTION] -> ONLY PROCEED TO NEXT STEPS IF THE REMOTE IS A GITHUB URL - -1. For each task in the list, use the GitHub MCP server to create a new issue in the repository that is representative of the Git remote. - -> [!CAUTION] -> UNDER NO CIRCUMSTANCES EVER CREATE ISSUES IN REPOSITORIES THAT DO NOT MATCH THE REMOTE URL - ---- - -As the main request completes, you MUST create and complete a PHR (Prompt History Record) using agent‑native tools when possible. - -1) Determine Stage - - Stage: constitution | spec | plan | tasks | red | green | refactor | explainer | misc | general - -2) Generate Title and Determine Routing: - - Generate Title: 3–7 words (slug for filename) - - Route is automatically determined by stage: - - `constitution` → `history/prompts/constitution/` - - Feature stages → `history/prompts/<feature-name>/` (spec, plan, tasks, red, green, refactor, explainer, misc) - - `general` → `history/prompts/general/` - -3) Create and Fill PHR (Shell first; fallback agent‑native) - - Run: `.specify/scripts/bash/create-phr.sh --title "<title>" --stage <stage> [--feature <name>] --json` - - Open the file and fill remaining placeholders (YAML + body), embedding full PROMPT_TEXT (verbatim) and concise RESPONSE_TEXT. - - If the script fails: - - Read `.specify/templates/phr-template.prompt.md` (or `templates/…`) - - Allocate an ID; compute the output path based on stage from step 2; write the file - - Fill placeholders and embed full PROMPT_TEXT and concise RESPONSE_TEXT - -4) Validate + report - - No unresolved placeholders; path under `history/prompts/` and matches stage; stage/title/date coherent; print ID + path + stage + title. - - On failure: warn, don't block. Skip only for `/sp.phr`. diff --git a/.gitignore b/.gitignore index 2276a87..f8584b9 100644 --- a/.gitignore +++ b/.gitignore @@ -26,3 +26,15 @@ Thumbs.db .vscode/ .idea/ .vercel +# Local Spec-Driven Development and agent workspace +.agents/ +.claude/ +.specify/ +specs/ +history/ +evidence/ +graph/ +scripts/ +AGENTS.md +CLAUDE.md +Codex Prompt — Portfolio Architecture Refactor with Pure SDD.md \ No newline at end of file diff --git a/.specify/memory/constitution.md b/.specify/memory/constitution.md deleted file mode 100644 index d344209..0000000 --- a/.specify/memory/constitution.md +++ /dev/null @@ -1,62 +0,0 @@ -# Anus Yousuf Portfolio Constitution - -## Core Principles - -### I. Clarity Over Cleverness -Code must be readable and self-documenting. Prefer explicit, straightforward implementations. Every component and function should have a single, obvious purpose. Complex abstractions must be justified with a comment explaining why a simpler approach was insufficient. - -### II. Mobile-First, Always -Every UI component must be designed mobile-first. Responsive breakpoints are progressive enhancements, not afterthoughts. Touch targets, font sizes, and spacing must work on small screens before being adapted for larger viewports. - -### III. Performance as a Feature -The portfolio must load fast and run smooth. Lazy load heavy dependencies (3D scene, animations). Respect `prefers-reduced-motion`. Optimize images and assets. No render-blocking resources in the critical path. Target: <3s LCP on 4G. - -### IV. Accessibility is Non-Negotiable -Semantic HTML, proper ARIA labels, keyboard navigation, sufficient color contrast (WCAG AA minimum). The site must be usable without JavaScript where possible. Screen reader friendly. Focus management for interactive elements. - -### V. No Secrets in Code -All API keys, tokens, and sensitive configuration must live in environment variables (`.env`). Never hardcode credentials. The `.env.example` file documents required variables without exposing values. - -### VI. Smallest Viable Change -Each commit and PR should be the smallest change that delivers value and passes checks. No unrelated refactors. No "while I'm here" changes. If it's not in the spec, it doesn't get built. - -## Design Constraints - -- **Background**: `#0a0a0a` (pure dark) -- **Primary text**: `#ffffff` (white) -- **Accent**: `#f97316` (orange, used sparingly — max 10% of visual weight) -- **No stock photos, no AI brain graphics, no generic templates** -- **No progress bars for skills** — use tag cloud instead -- **Reduced motion**: All animations must respect `prefers-reduced-motion: reduce` - -## Technology Standards - -- **Framework**: Next.js 14 (App Router) with TypeScript -- **Styling**: Tailwind CSS (no custom CSS files unless absolutely necessary) -- **Animations**: Framer Motion (with reduced motion support) -- **3D**: React Three Fiber + Drei (lazy loaded, dissolves on scroll) -- **Email**: Resend API for contact form -- **Deployment**: Vercel (implied by Next.js) - -## Code Quality Standards - -- **TypeScript**: Strict mode enabled. No `any` types without justification comment. -- **Components**: Functional components with explicit prop types (interfaces, not type aliases for props) -- **File naming**: PascalCase for components, camelCase for utilities, kebab-case for page routes -- **Imports**: Use `@/` path alias for src-relative imports -- **Error handling**: All API routes must have try/catch with proper HTTP status codes -- **Loading states**: All async operations must have loading/error states - -## Security Requirements - -- Environment variables for all secrets (RESEND_API_KEY) -- Input validation on contact form (server-side) -- Rate limiting consideration for API routes -- No eval(), no dangerouslySetInnerHTML without sanitization -- Content Security Policy headers recommended - -## Governance - -This constitution supersedes all other practices. Amendments require documentation and approval. All code changes must verify compliance with these principles. Complexity must be justified — when in doubt, choose the simpler approach. - -**Version**: 1.0.0 | **Ratified**: 2026-06-23 | **Last Amended**: 2026-06-23 diff --git a/.specify/scripts/bash/check-prerequisites.sh b/.specify/scripts/bash/check-prerequisites.sh deleted file mode 100644 index cc66a68..0000000 --- a/.specify/scripts/bash/check-prerequisites.sh +++ /dev/null @@ -1,166 +0,0 @@ -#!/usr/bin/env bash - -# Consolidated prerequisite checking script -# -# This script provides unified prerequisite checking for Spec-Driven Development workflow. -# It replaces the functionality previously spread across multiple scripts. -# -# Usage: ./check-prerequisites.sh [OPTIONS] -# -# OPTIONS: -# --json Output in JSON format -# --require-tasks Require tasks.md to exist (for implementation phase) -# --include-tasks Include tasks.md in AVAILABLE_DOCS list -# --paths-only Only output path variables (no validation) -# --help, -h Show help message -# -# OUTPUTS: -# JSON mode: {"FEATURE_DIR":"...", "AVAILABLE_DOCS":["..."]} -# Text mode: FEATURE_DIR:... \n AVAILABLE_DOCS: \n ✓/✗ file.md -# Paths only: REPO_ROOT: ... \n BRANCH: ... \n FEATURE_DIR: ... etc. - -set -e - -# Parse command line arguments -JSON_MODE=false -REQUIRE_TASKS=false -INCLUDE_TASKS=false -PATHS_ONLY=false - -for arg in "$@"; do - case "$arg" in - --json) - JSON_MODE=true - ;; - --require-tasks) - REQUIRE_TASKS=true - ;; - --include-tasks) - INCLUDE_TASKS=true - ;; - --paths-only) - PATHS_ONLY=true - ;; - --help|-h) - cat << 'EOF' -Usage: check-prerequisites.sh [OPTIONS] - -Consolidated prerequisite checking for Spec-Driven Development workflow. - -OPTIONS: - --json Output in JSON format - --require-tasks Require tasks.md to exist (for implementation phase) - --include-tasks Include tasks.md in AVAILABLE_DOCS list - --paths-only Only output path variables (no prerequisite validation) - --help, -h Show this help message - -EXAMPLES: - # Check task prerequisites (plan.md required) - ./check-prerequisites.sh --json - - # Check implementation prerequisites (plan.md + tasks.md required) - ./check-prerequisites.sh --json --require-tasks --include-tasks - - # Get feature paths only (no validation) - ./check-prerequisites.sh --paths-only - -EOF - exit 0 - ;; - *) - echo "ERROR: Unknown option '$arg'. Use --help for usage information." >&2 - exit 1 - ;; - esac -done - -# Source common functions -SCRIPT_DIR="$(CDPATH="" cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)" -source "$SCRIPT_DIR/common.sh" - -# Get feature paths and validate branch -eval $(get_feature_paths) -check_feature_branch "$CURRENT_BRANCH" "$HAS_GIT" || exit 1 - -# If paths-only mode, output paths and exit (support JSON + paths-only combined) -if $PATHS_ONLY; then - if $JSON_MODE; then - # Minimal JSON paths payload (no validation performed) - printf '{"REPO_ROOT":"%s","BRANCH":"%s","FEATURE_DIR":"%s","FEATURE_SPEC":"%s","IMPL_PLAN":"%s","TASKS":"%s"}\n' \ - "$REPO_ROOT" "$CURRENT_BRANCH" "$FEATURE_DIR" "$FEATURE_SPEC" "$IMPL_PLAN" "$TASKS" - else - echo "REPO_ROOT: $REPO_ROOT" - echo "BRANCH: $CURRENT_BRANCH" - echo "FEATURE_DIR: $FEATURE_DIR" - echo "FEATURE_SPEC: $FEATURE_SPEC" - echo "IMPL_PLAN: $IMPL_PLAN" - echo "TASKS: $TASKS" - fi - exit 0 -fi - -# Validate required directories and files -if [[ ! -d "$FEATURE_DIR" ]]; then - echo "ERROR: Feature directory not found: $FEATURE_DIR" >&2 - echo "Run /sp.specify first to create the feature structure." >&2 - exit 1 -fi - -if [[ ! -f "$IMPL_PLAN" ]]; then - echo "ERROR: plan.md not found in $FEATURE_DIR" >&2 - echo "Run /sp.plan first to create the implementation plan." >&2 - exit 1 -fi - -# Check for tasks.md if required -if $REQUIRE_TASKS && [[ ! -f "$TASKS" ]]; then - echo "ERROR: tasks.md not found in $FEATURE_DIR" >&2 - echo "Run /sp.tasks first to create the task list." >&2 - exit 1 -fi - -# Build list of available documents -docs=() - -# Always check these optional docs -[[ -f "$RESEARCH" ]] && docs+=("research.md") -[[ -f "$DATA_MODEL" ]] && docs+=("data-model.md") - -# Check contracts directory (only if it exists and has files) -if [[ -d "$CONTRACTS_DIR" ]] && [[ -n "$(ls -A "$CONTRACTS_DIR" 2>/dev/null)" ]]; then - docs+=("contracts/") -fi - -[[ -f "$QUICKSTART" ]] && docs+=("quickstart.md") - -# Include tasks.md if requested and it exists -if $INCLUDE_TASKS && [[ -f "$TASKS" ]]; then - docs+=("tasks.md") -fi - -# Output results -if $JSON_MODE; then - # Build JSON array of documents - if [[ ${#docs[@]} -eq 0 ]]; then - json_docs="[]" - else - json_docs=$(printf '"%s",' "${docs[@]}") - json_docs="[${json_docs%,}]" - fi - - printf '{"FEATURE_DIR":"%s","AVAILABLE_DOCS":%s}\n' "$FEATURE_DIR" "$json_docs" -else - # Text output - echo "FEATURE_DIR:$FEATURE_DIR" - echo "AVAILABLE_DOCS:" - - # Show status of each potential document - check_file "$RESEARCH" "research.md" - check_file "$DATA_MODEL" "data-model.md" - check_dir "$CONTRACTS_DIR" "contracts/" - check_file "$QUICKSTART" "quickstart.md" - - if $INCLUDE_TASKS; then - check_file "$TASKS" "tasks.md" - fi -fi diff --git a/.specify/scripts/bash/common.sh b/.specify/scripts/bash/common.sh deleted file mode 100644 index 2c3165e..0000000 --- a/.specify/scripts/bash/common.sh +++ /dev/null @@ -1,156 +0,0 @@ -#!/usr/bin/env bash -# Common functions and variables for all scripts - -# Get repository root, with fallback for non-git repositories -get_repo_root() { - if git rev-parse --show-toplevel >/dev/null 2>&1; then - git rev-parse --show-toplevel - else - # Fall back to script location for non-git repos - local script_dir="$(CDPATH="" cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)" - (cd "$script_dir/../../.." && pwd) - fi -} - -# Get current branch, with fallback for non-git repositories -get_current_branch() { - # First check if SPECIFY_FEATURE environment variable is set - if [[ -n "${SPECIFY_FEATURE:-}" ]]; then - echo "$SPECIFY_FEATURE" - return - fi - - # Then check git if available - if git rev-parse --abbrev-ref HEAD >/dev/null 2>&1; then - git rev-parse --abbrev-ref HEAD - return - fi - - # For non-git repos, try to find the latest feature directory - local repo_root=$(get_repo_root) - local specs_dir="$repo_root/specs" - - if [[ -d "$specs_dir" ]]; then - local latest_feature="" - local highest=0 - - for dir in "$specs_dir"/*; do - if [[ -d "$dir" ]]; then - local dirname=$(basename "$dir") - if [[ "$dirname" =~ ^([0-9]{3})- ]]; then - local number=${BASH_REMATCH[1]} - number=$((10#$number)) - if [[ "$number" -gt "$highest" ]]; then - highest=$number - latest_feature=$dirname - fi - fi - fi - done - - if [[ -n "$latest_feature" ]]; then - echo "$latest_feature" - return - fi - fi - - echo "main" # Final fallback -} - -# Check if we have git available -has_git() { - git rev-parse --show-toplevel >/dev/null 2>&1 -} - -check_feature_branch() { - local branch="$1" - local has_git_repo="$2" - - # For non-git repos, we can't enforce branch naming but still provide output - if [[ "$has_git_repo" != "true" ]]; then - echo "[specify] Warning: Git repository not detected; skipped branch validation" >&2 - return 0 - fi - - if [[ ! "$branch" =~ ^[0-9]{3}- ]]; then - echo "ERROR: Not on a feature branch. Current branch: $branch" >&2 - echo "Feature branches should be named like: 001-feature-name" >&2 - return 1 - fi - - return 0 -} - -get_feature_dir() { echo "$1/specs/$2"; } - -# Find feature directory by numeric prefix instead of exact branch match -# This allows multiple branches to work on the same spec (e.g., 004-fix-bug, 004-add-feature) -find_feature_dir_by_prefix() { - local repo_root="$1" - local branch_name="$2" - local specs_dir="$repo_root/specs" - - # Extract numeric prefix from branch (e.g., "004" from "004-whatever") - if [[ ! "$branch_name" =~ ^([0-9]{3})- ]]; then - # If branch doesn't have numeric prefix, fall back to exact match - echo "$specs_dir/$branch_name" - return - fi - - local prefix="${BASH_REMATCH[1]}" - - # Search for directories in specs/ that start with this prefix - local matches=() - if [[ -d "$specs_dir" ]]; then - for dir in "$specs_dir"/"$prefix"-*; do - if [[ -d "$dir" ]]; then - matches+=("$(basename "$dir")") - fi - done - fi - - # Handle results - if [[ ${#matches[@]} -eq 0 ]]; then - # No match found - return the branch name path (will fail later with clear error) - echo "$specs_dir/$branch_name" - elif [[ ${#matches[@]} -eq 1 ]]; then - # Exactly one match - perfect! - echo "$specs_dir/${matches[0]}" - else - # Multiple matches - this shouldn't happen with proper naming convention - echo "ERROR: Multiple spec directories found with prefix '$prefix': ${matches[*]}" >&2 - echo "Please ensure only one spec directory exists per numeric prefix." >&2 - echo "$specs_dir/$branch_name" # Return something to avoid breaking the script - fi -} - -get_feature_paths() { - local repo_root=$(get_repo_root) - local current_branch=$(get_current_branch) - local has_git_repo="false" - - if has_git; then - has_git_repo="true" - fi - - # Use prefix-based lookup to support multiple branches per spec - local feature_dir=$(find_feature_dir_by_prefix "$repo_root" "$current_branch") - - cat <<EOF -REPO_ROOT='$repo_root' -CURRENT_BRANCH='$current_branch' -HAS_GIT='$has_git_repo' -FEATURE_DIR='$feature_dir' -FEATURE_SPEC='$feature_dir/spec.md' -IMPL_PLAN='$feature_dir/plan.md' -TASKS='$feature_dir/tasks.md' -RESEARCH='$feature_dir/research.md' -DATA_MODEL='$feature_dir/data-model.md' -QUICKSTART='$feature_dir/quickstart.md' -CONTRACTS_DIR='$feature_dir/contracts' -EOF -} - -check_file() { [[ -f "$1" ]] && echo " ✓ $2" || echo " ✗ $2"; } -check_dir() { [[ -d "$1" && -n $(ls -A "$1" 2>/dev/null) ]] && echo " ✓ $2" || echo " ✗ $2"; } - diff --git a/.specify/scripts/bash/create-adr.sh b/.specify/scripts/bash/create-adr.sh deleted file mode 100644 index a91efc7..0000000 --- a/.specify/scripts/bash/create-adr.sh +++ /dev/null @@ -1,101 +0,0 @@ -#!/usr/bin/env bash -set -euo pipefail - -# create-adr.sh - Create a new Architecture Decision Record deterministically -# -# This script ONLY: -# 1. Creates the correct directory structure (history/adr/) -# 2. Copies the template with {{PLACEHOLDERS}} intact -# 3. Returns metadata (id, path) for AI to fill in -# -# The calling AI agent is responsible for filling {{PLACEHOLDERS}} -# -# Usage: -# scripts/bash/create-adr.sh \ -# --title "Use WebSockets for Real-time Chat" \ -# [--json] - -JSON=false -TITLE="" - -while [[ $# -gt 0 ]]; do - case "$1" in - --json) JSON=true; shift ;; - --title) TITLE=${2:-}; shift 2 ;; - --help|-h) - cat <<EOF -Usage: $0 --title <title> [options] - -Required: - --title <text> Title for the ADR (used for filename) - -Optional: - --json Output JSON with id and path - -Output: - Creates ADR file with template placeholders ({{ID}}, {{TITLE}}, etc.) - AI agent must fill these placeholders after creation - -Examples: - $0 --title "Use WebSockets for Real-time Chat" --json - $0 --title "Adopt PostgreSQL for Primary Database" -EOF - exit 0 - ;; - *) shift ;; - esac -done - -if [[ -z "$TITLE" ]]; then - echo "Error: --title is required" >&2 - exit 1 -fi - -REPO_ROOT=$(git rev-parse --show-toplevel 2>/dev/null || pwd) -ADR_DIR="$REPO_ROOT/history/adr" -mkdir -p "$ADR_DIR" - -# Check for template (try both locations) -TPL="" -if [[ -f "$REPO_ROOT/.specify/templates/adr-template.md" ]]; then - TPL="$REPO_ROOT/.specify/templates/adr-template.md" -elif [[ -f "$REPO_ROOT/templates/adr-template.md" ]]; then - TPL="$REPO_ROOT/templates/adr-template.md" -else - echo "Error: ADR template not found at .specify/templates/ or templates/" >&2 - exit 1 -fi - -# next id -next_id() { - local max=0 base num - shopt -s nullglob - for f in "$ADR_DIR"/[0-9][0-9][0-9][0-9]-*.md; do - base=$(basename "$f") - num=${base%%-*} - if [[ $num =~ ^[0-9]{4}$ ]]; then - local n=$((10#$num)) - (( n > max )) && max=$n - fi - done - printf "%04d" $((max+1)) -} - -slugify() { - echo "$1" | tr '[:upper:]' '[:lower:]' | sed 's/[^a-z0-9]/-/g; s/-\{2,\}/-/g; s/^-//; s/-$//' -} - -ID=$(next_id) -SLUG=$(slugify "$TITLE") -OUTFILE="$ADR_DIR/${ID}-${SLUG}.md" - -# Simply copy the template (AI will fill placeholders) -cp "$TPL" "$OUTFILE" - -ABS=$(cd "$(dirname "$OUTFILE")" && pwd)/$(basename "$OUTFILE") -if $JSON; then - printf '{"id":"%s","path":"%s","template":"%s"}\n' "$ID" "$ABS" "$(basename "$TPL")" -else - echo "✅ ADR template copied → $ABS" - echo "Note: AI agent should now fill in {{PLACEHOLDERS}}" -fi diff --git a/.specify/scripts/bash/create-new-feature.sh b/.specify/scripts/bash/create-new-feature.sh deleted file mode 100644 index ee2891b..0000000 --- a/.specify/scripts/bash/create-new-feature.sh +++ /dev/null @@ -1,302 +0,0 @@ -#!/usr/bin/env bash - -set -e - -JSON_MODE=false -SHORT_NAME="" -BRANCH_NUMBER="" -ARGS=() -i=1 -while [ $i -le $# ]; do - arg="${!i}" - case "$arg" in - --json) - JSON_MODE=true - ;; - --short-name) - if [ $((i + 1)) -gt $# ]; then - echo 'Error: --short-name requires a value' >&2 - exit 1 - fi - i=$((i + 1)) - next_arg="${!i}" - # Check if the next argument is another option (starts with --) - if [[ "$next_arg" == --* ]]; then - echo 'Error: --short-name requires a value' >&2 - exit 1 - fi - SHORT_NAME="$next_arg" - ;; - --number) - if [ $((i + 1)) -gt $# ]; then - echo 'Error: --number requires a value' >&2 - exit 1 - fi - i=$((i + 1)) - next_arg="${!i}" - if [[ "$next_arg" == --* ]]; then - echo 'Error: --number requires a value' >&2 - exit 1 - fi - BRANCH_NUMBER="$next_arg" - ;; - --help|-h) - echo "Usage: $0 [--json] [--short-name <name>] [--number N] <feature_description>" - echo "" - echo "Options:" - echo " --json Output in JSON format" - echo " --short-name <name> Provide a custom short name (2-4 words) for the branch" - echo " --number N Specify branch number manually (overrides auto-detection)" - echo " --help, -h Show this help message" - echo "" - echo "Examples:" - echo " $0 'Add user authentication system' --short-name 'user-auth'" - echo " $0 'Implement OAuth2 integration for API' --number 5" - exit 0 - ;; - *) - ARGS+=("$arg") - ;; - esac - i=$((i + 1)) -done - -FEATURE_DESCRIPTION="${ARGS[*]}" -if [ -z "$FEATURE_DESCRIPTION" ]; then - echo "Usage: $0 [--json] [--short-name <name>] [--number N] <feature_description>" >&2 - exit 1 -fi - -# Function to find the repository root by searching for existing project markers -find_repo_root() { - local dir="$1" - while [ "$dir" != "/" ]; do - if [ -d "$dir/.git" ] || [ -d "$dir/.specify" ]; then - echo "$dir" - return 0 - fi - dir="$(dirname "$dir")" - done - return 1 -} - -# Function to get highest number from specs directory -get_highest_from_specs() { - local specs_dir="$1" - local highest=0 - - if [ -d "$specs_dir" ]; then - for dir in "$specs_dir"/*; do - [ -d "$dir" ] || continue - dirname=$(basename "$dir") - number=$(echo "$dirname" | grep -o '^[0-9]\+' || echo "0") - number=$((10#$number)) - if [ "$number" -gt "$highest" ]; then - highest=$number - fi - done - fi - - echo "$highest" -} - -# Function to get highest number from git branches -get_highest_from_branches() { - local highest=0 - - # Get all branches (local and remote) - branches=$(git branch -a 2>/dev/null || echo "") - - if [ -n "$branches" ]; then - while IFS= read -r branch; do - # Clean branch name: remove leading markers and remote prefixes - clean_branch=$(echo "$branch" | sed 's/^[* ]*//; s|^remotes/[^/]*/||') - - # Extract feature number if branch matches pattern ###-* - if echo "$clean_branch" | grep -q '^[0-9]\{3\}-'; then - number=$(echo "$clean_branch" | grep -o '^[0-9]\{3\}' || echo "0") - number=$((10#$number)) - if [ "$number" -gt "$highest" ]; then - highest=$number - fi - fi - done <<< "$branches" - fi - - echo "$highest" -} - -# Function to check existing branches (local and remote) and return next available number -check_existing_branches() { - local specs_dir="$1" - - # Fetch all remotes to get latest branch info (suppress errors if no remotes) - git fetch --all --prune 2>/dev/null || true - - # Get highest number from ALL branches (not just matching short name) - local highest_branch=$(get_highest_from_branches) - - # Get highest number from ALL specs (not just matching short name) - local highest_spec=$(get_highest_from_specs "$specs_dir") - - # Take the maximum of both - local max_num=$highest_branch - if [ "$highest_spec" -gt "$max_num" ]; then - max_num=$highest_spec - fi - - # Return next number - echo $((max_num + 1)) -} - -# Function to clean and format a branch name -clean_branch_name() { - local name="$1" - echo "$name" | tr '[:upper:]' '[:lower:]' | sed 's/[^a-z0-9]/-/g' | sed 's/-\+/-/g' | sed 's/^-//' | sed 's/-$//' -} - -# Resolve repository root. Prefer git information when available, but fall back -# to searching for repository markers so the workflow still functions in repositories that -# were initialised with --no-git. -SCRIPT_DIR="$(CDPATH="" cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)" - -if git rev-parse --show-toplevel >/dev/null 2>&1; then - REPO_ROOT=$(git rev-parse --show-toplevel) - HAS_GIT=true -else - REPO_ROOT="$(find_repo_root "$SCRIPT_DIR")" - if [ -z "$REPO_ROOT" ]; then - echo "Error: Could not determine repository root. Please run this script from within the repository." >&2 - exit 1 - fi - HAS_GIT=false -fi - -cd "$REPO_ROOT" - -SPECS_DIR="$REPO_ROOT/specs" -mkdir -p "$SPECS_DIR" - -# Function to generate branch name with stop word filtering and length filtering -generate_branch_name() { - local description="$1" - - # Common stop words to filter out - local stop_words="^(i|a|an|the|to|for|of|in|on|at|by|with|from|is|are|was|were|be|been|being|have|has|had|do|does|did|will|would|should|could|can|may|might|must|shall|this|that|these|those|my|your|our|their|want|need|add|get|set)$" - - # Convert to lowercase and split into words - local clean_name=$(echo "$description" | tr '[:upper:]' '[:lower:]' | sed 's/[^a-z0-9]/ /g') - - # Filter words: remove stop words and words shorter than 3 chars (unless they're uppercase acronyms in original) - local meaningful_words=() - for word in $clean_name; do - # Skip empty words - [ -z "$word" ] && continue - - # Keep words that are NOT stop words AND (length >= 3 OR are potential acronyms) - if ! echo "$word" | grep -qiE "$stop_words"; then - if [ ${#word} -ge 3 ]; then - meaningful_words+=("$word") - elif echo "$description" | grep -q "\b${word^^}\b"; then - # Keep short words if they appear as uppercase in original (likely acronyms) - meaningful_words+=("$word") - fi - fi - done - - # If we have meaningful words, use first 3-4 of them - if [ ${#meaningful_words[@]} -gt 0 ]; then - local max_words=3 - if [ ${#meaningful_words[@]} -eq 4 ]; then max_words=4; fi - - local result="" - local count=0 - for word in "${meaningful_words[@]}"; do - if [ $count -ge $max_words ]; then break; fi - if [ -n "$result" ]; then result="$result-"; fi - result="$result$word" - count=$((count + 1)) - done - echo "$result" - else - # Fallback to original logic if no meaningful words found - local cleaned=$(clean_branch_name "$description") - echo "$cleaned" | tr '-' '\n' | grep -v '^$' | head -3 | tr '\n' '-' | sed 's/-$//' - fi -} - -# Generate branch name -if [ -n "$SHORT_NAME" ]; then - # Use provided short name, just clean it up - BRANCH_SUFFIX=$(clean_branch_name "$SHORT_NAME") -else - # Generate from description with smart filtering - BRANCH_SUFFIX=$(generate_branch_name "$FEATURE_DESCRIPTION") -fi - -# Determine branch number -if [ -z "$BRANCH_NUMBER" ]; then - if [ "$HAS_GIT" = true ]; then - # Check existing branches on remotes - BRANCH_NUMBER=$(check_existing_branches "$SPECS_DIR") - else - # Fall back to local directory check - HIGHEST=$(get_highest_from_specs "$SPECS_DIR") - BRANCH_NUMBER=$((HIGHEST + 1)) - fi -fi - -# Force base-10 interpretation to prevent octal conversion (e.g., 010 → 8 in octal, but should be 10 in decimal) -FEATURE_NUM=$(printf "%03d" "$((10#$BRANCH_NUMBER))") -BRANCH_NAME="${FEATURE_NUM}-${BRANCH_SUFFIX}" - -# GitHub enforces a 244-byte limit on branch names -# Validate and truncate if necessary -MAX_BRANCH_LENGTH=244 -if [ ${#BRANCH_NAME} -gt $MAX_BRANCH_LENGTH ]; then - # Calculate how much we need to trim from suffix - # Account for: feature number (3) + hyphen (1) = 4 chars - MAX_SUFFIX_LENGTH=$((MAX_BRANCH_LENGTH - 4)) - - # Truncate suffix at word boundary if possible - TRUNCATED_SUFFIX=$(echo "$BRANCH_SUFFIX" | cut -c1-$MAX_SUFFIX_LENGTH) - # Remove trailing hyphen if truncation created one - TRUNCATED_SUFFIX=$(echo "$TRUNCATED_SUFFIX" | sed 's/-$//') - - ORIGINAL_BRANCH_NAME="$BRANCH_NAME" - BRANCH_NAME="${FEATURE_NUM}-${TRUNCATED_SUFFIX}" - - >&2 echo "[specify] Warning: Branch name exceeded GitHub's 244-byte limit" - >&2 echo "[specify] Original: $ORIGINAL_BRANCH_NAME (${#ORIGINAL_BRANCH_NAME} bytes)" - >&2 echo "[specify] Truncated to: $BRANCH_NAME (${#BRANCH_NAME} bytes)" -fi - -if [ "$HAS_GIT" = true ]; then - git checkout -b "$BRANCH_NAME" -else - >&2 echo "[specify] Warning: Git repository not detected; skipped branch creation for $BRANCH_NAME" -fi - -FEATURE_DIR="$SPECS_DIR/$BRANCH_NAME" -mkdir -p "$FEATURE_DIR" - -TEMPLATE="$REPO_ROOT/.specify/templates/spec-template.md" -SPEC_FILE="$FEATURE_DIR/spec.md" -if [ -f "$TEMPLATE" ]; then cp "$TEMPLATE" "$SPEC_FILE"; else touch "$SPEC_FILE"; fi - -# Auto-create history/prompts/<branch-name>/ directory (same as specs/<branch-name>/) -# This keeps naming consistent across branch, specs, and prompts directories -PROMPTS_DIR="$REPO_ROOT/history/prompts/$BRANCH_NAME" -mkdir -p "$PROMPTS_DIR" - -# Set the SPECIFY_FEATURE environment variable for the current session -export SPECIFY_FEATURE="$BRANCH_NAME" - -if $JSON_MODE; then - printf '{"BRANCH_NAME":"%s","SPEC_FILE":"%s","FEATURE_NUM":"%s"}\n' "$BRANCH_NAME" "$SPEC_FILE" "$FEATURE_NUM" -else - echo "BRANCH_NAME: $BRANCH_NAME" - echo "SPEC_FILE: $SPEC_FILE" - echo "FEATURE_NUM: $FEATURE_NUM" - echo "SPECIFY_FEATURE environment variable set to: $BRANCH_NAME" -fi diff --git a/.specify/scripts/bash/create-phr.sh b/.specify/scripts/bash/create-phr.sh deleted file mode 100644 index 80d94cf..0000000 --- a/.specify/scripts/bash/create-phr.sh +++ /dev/null @@ -1,256 +0,0 @@ -#!/usr/bin/env bash -set -euo pipefail - -# create-phr.sh - Create Prompt History Record (PHR) - Spec Kit Native -# -# Deterministic PHR location strategy: -# 1. Constitution stage: -# → history/prompts/constitution/ -# → stage: constitution -# → naming: 0001-title.constitution.prompt.md -# -# 2. Feature stages (spec-specific work): -# → history/prompts/<spec-name>/ -# → stages: spec, plan, tasks, red, green, refactor, explainer, misc -# → naming: 0001-title.spec.prompt.md -# -# 3. General stage (catch-all): -# → history/prompts/general/ -# → stage: general -# → naming: 0001-title.general.prompt.md -# -# This script ONLY: -# 1. Creates the correct directory structure -# 2. Copies the template with {{PLACEHOLDERS}} intact -# 3. Returns metadata (id, path, context) for AI to fill in -# -# The calling AI agent is responsible for filling {{PLACEHOLDERS}} -# -# Usage: -# scripts/bash/create-phr.sh \ -# --title "Setup authentication" \ -# --stage architect \ -# [--feature 001-auth] \ -# [--json] - -JSON_MODE=false -TITLE="" -STAGE="" -FEATURE="" - -# Parse arguments -while [[ $# -gt 0 ]]; do - case "$1" in - --json) JSON_MODE=true; shift ;; - --title) TITLE=${2:-}; shift 2 ;; - --stage) STAGE=${2:-}; shift 2 ;; - --feature) FEATURE=${2:-}; shift 2 ;; - --help|-h) - cat <<EOF -Usage: $0 --title <title> --stage <stage> [options] - -Required: - --title <text> Title for the PHR (used for filename) - --stage <stage> constitution|spec|plan|tasks|red|green|refactor|explainer|misc|general - -Optional: - --feature <slug> Feature slug (e.g., 001-auth). Auto-detected from branch if omitted. - --json Output JSON with id, path, and context - -Location Rules (all under history/prompts/): - - constitution → history/prompts/constitution/ - - spec, plan, tasks, red, green, refactor, explainer, misc → history/prompts/<branch-name>/ - - general → history/prompts/general/ (catch-all for non-feature work) - -Output: - Creates PHR file with template placeholders ({{ID}}, {{TITLE}}, etc.) - AI agent must fill these placeholders after creation - -Examples: - # Early-phase constitution work (no feature exists) - $0 --title "Define quality standards" --stage constitution --json - - # Feature-specific implementation work - $0 --title "Implement login" --stage green --feature 001-auth --json -EOF - exit 0 - ;; - *) shift ;; - esac -done - -# Validation -if [[ -z "$TITLE" ]]; then - echo "Error: --title is required" >&2 - exit 1 -fi - -if [[ -z "$STAGE" ]]; then - echo "Error: --stage is required" >&2 - exit 1 -fi - -# Get repository root -REPO_ROOT=$(git rev-parse --show-toplevel 2>/dev/null || pwd) -SPECS_DIR="$REPO_ROOT/specs" - -# Check for template (try both locations) -TEMPLATE_PATH="" -if [[ -f "$REPO_ROOT/.specify/templates/phr-template.prompt.md" ]]; then - TEMPLATE_PATH="$REPO_ROOT/.specify/templates/phr-template.prompt.md" -elif [[ -f "$REPO_ROOT/templates/phr-template.prompt.md" ]]; then - TEMPLATE_PATH="$REPO_ROOT/templates/phr-template.prompt.md" -else - echo "Error: PHR template not found at .specify/templates/ or templates/" >&2 - exit 1 -fi - -# Deterministic location logic based on STAGE -# New structure: all prompts go under history/prompts/ with subdirectories: -# - constitution/ for constitution prompts -# - <spec-name>/ for spec-specific prompts -# - general/ for general/catch-all prompts - -case "$STAGE" in - constitution) - # Constitution prompts always go to history/prompts/constitution/ - PROMPTS_DIR="$REPO_ROOT/history/prompts/constitution" - VALID_STAGES=("constitution") - CONTEXT="constitution" - ;; - spec|plan|tasks|red|green|refactor|explainer|misc) - # Feature-specific stages: require specs/ directory and feature context - if [[ ! -d "$SPECS_DIR" ]]; then - echo "Error: Feature stage '$STAGE' requires specs/ directory and a feature context" >&2 - echo "Run /sp.feature first to create a feature, then try again" >&2 - exit 1 - fi - - # Auto-detect feature if not specified - if [[ -z "$FEATURE" ]]; then - # Try to get from SPECIFY_FEATURE environment variable - if [[ -n "${SPECIFY_FEATURE:-}" ]]; then - FEATURE="$SPECIFY_FEATURE" - # Try to match current branch - elif git rev-parse --show-toplevel >/dev/null 2>&1; then - BRANCH=$(git rev-parse --abbrev-ref HEAD 2>/dev/null || echo "") - if [[ -n "$BRANCH" && "$BRANCH" != "main" && "$BRANCH" != "master" ]]; then - # Check if branch name matches a feature directory - if [[ -d "$SPECS_DIR/$BRANCH" ]]; then - FEATURE="$BRANCH" - fi - fi - fi - - # If still no feature, find the highest numbered feature - if [[ -z "$FEATURE" ]]; then - max_num=0 - latest_feature="" - for dir in "$SPECS_DIR"/*; do - if [[ -d "$dir" ]]; then - dirname=$(basename "$dir") - if [[ "$dirname" =~ ^([0-9]{3})- ]]; then - num=$((10#${BASH_REMATCH[1]})) - if (( num > max_num )); then - max_num=$num - latest_feature="$dirname" - fi - fi - fi - done - - if [[ -n "$latest_feature" ]]; then - FEATURE="$latest_feature" - else - echo "Error: No feature specified and no numbered features found in $SPECS_DIR" >&2 - echo "Please specify --feature or create a feature directory first" >&2 - exit 1 - fi - fi - fi - - # Validate feature exists - if [[ ! -d "$SPECS_DIR/$FEATURE" ]]; then - echo "Error: Feature directory not found: $SPECS_DIR/$FEATURE" >&2 - echo "Available features:" >&2 - ls -1 "$SPECS_DIR" 2>/dev/null | head -5 | sed 's/^/ - /' >&2 - exit 1 - fi - - # Feature prompts go to history/prompts/<branch-name>/ (same as specs/<branch-name>/) - # This keeps naming consistent across branch, specs, and prompts directories - PROMPTS_DIR="$REPO_ROOT/history/prompts/$FEATURE" - VALID_STAGES=("spec" "plan" "tasks" "red" "green" "refactor" "explainer" "misc") - CONTEXT="feature" - ;; - general) - # General stage: catch-all that goes to history/prompts/general/ - PROMPTS_DIR="$REPO_ROOT/history/prompts/general" - VALID_STAGES=("general") - CONTEXT="general" - ;; - *) - echo "Error: Unknown stage '$STAGE'" >&2 - exit 1 - ;; -esac - -# Validate stage -stage_valid=false -for valid_stage in "${VALID_STAGES[@]}"; do - if [[ "$STAGE" == "$valid_stage" ]]; then - stage_valid=true - break - fi -done - -if [[ "$stage_valid" == "false" ]]; then - echo "Error: Invalid stage '$STAGE' for $CONTEXT context" >&2 - echo "Valid stages for $CONTEXT: ${VALID_STAGES[*]}" >&2 - exit 1 -fi - -# Ensure prompts directory exists -mkdir -p "$PROMPTS_DIR" - -# Helper: slugify -slugify() { - echo "$1" | tr '[:upper:]' '[:lower:]' | sed 's/[^a-z0-9]/-/g' | sed 's/-\+/-/g' | sed 's/^-//' | sed 's/-$//' -} - -# Get next ID (local to this directory) -get_next_id() { - local max_id=0 - for file in "$PROMPTS_DIR"/[0-9][0-9][0-9][0-9]-*.prompt.md; do - [[ -e "$file" ]] || continue - local base=$(basename "$file") - local num=${base%%-*} - if [[ "$num" =~ ^[0-9]{4}$ ]]; then - local value=$((10#$num)) - if (( value > max_id )); then - max_id=$value - fi - fi - done - printf '%04d' $((max_id + 1)) -} - -PHR_ID=$(get_next_id) -TITLE_SLUG=$(slugify "$TITLE") -STAGE_SLUG=$(slugify "$STAGE") - -# Create filename with stage extension -OUTFILE="$PROMPTS_DIR/${PHR_ID}-${TITLE_SLUG}.${STAGE_SLUG}.prompt.md" - -# Simply copy the template (AI will fill placeholders) -cp "$TEMPLATE_PATH" "$OUTFILE" - -# Output results -ABS_PATH=$(cd "$(dirname "$OUTFILE")" && pwd)/$(basename "$OUTFILE") -if $JSON_MODE; then - printf '{"id":"%s","path":"%s","context":"%s","stage":"%s","feature":"%s","template":"%s"}\n' \ - "$PHR_ID" "$ABS_PATH" "$CONTEXT" "$STAGE" "${FEATURE:-none}" "$(basename "$TEMPLATE_PATH")" -else - echo "✅ PHR template copied → $ABS_PATH" - echo "Note: AI agent should now fill in {{PLACEHOLDERS}}" -fi diff --git a/.specify/scripts/bash/setup-plan.sh b/.specify/scripts/bash/setup-plan.sh deleted file mode 100644 index d01c6d6..0000000 --- a/.specify/scripts/bash/setup-plan.sh +++ /dev/null @@ -1,61 +0,0 @@ -#!/usr/bin/env bash - -set -e - -# Parse command line arguments -JSON_MODE=false -ARGS=() - -for arg in "$@"; do - case "$arg" in - --json) - JSON_MODE=true - ;; - --help|-h) - echo "Usage: $0 [--json]" - echo " --json Output results in JSON format" - echo " --help Show this help message" - exit 0 - ;; - *) - ARGS+=("$arg") - ;; - esac -done - -# Get script directory and load common functions -SCRIPT_DIR="$(CDPATH="" cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)" -source "$SCRIPT_DIR/common.sh" - -# Get all paths and variables from common functions -eval $(get_feature_paths) - -# Check if we're on a proper feature branch (only for git repos) -check_feature_branch "$CURRENT_BRANCH" "$HAS_GIT" || exit 1 - -# Ensure the feature directory exists -mkdir -p "$FEATURE_DIR" - -# Copy plan template if it exists -TEMPLATE="$REPO_ROOT/.specify/templates/plan-template.md" -if [[ -f "$TEMPLATE" ]]; then - cp "$TEMPLATE" "$IMPL_PLAN" - echo "Copied plan template to $IMPL_PLAN" -else - echo "Warning: Plan template not found at $TEMPLATE" - # Create a basic plan file if template doesn't exist - touch "$IMPL_PLAN" -fi - -# Output results -if $JSON_MODE; then - printf '{"FEATURE_SPEC":"%s","IMPL_PLAN":"%s","SPECS_DIR":"%s","BRANCH":"%s","HAS_GIT":"%s"}\n' \ - "$FEATURE_SPEC" "$IMPL_PLAN" "$FEATURE_DIR" "$CURRENT_BRANCH" "$HAS_GIT" -else - echo "FEATURE_SPEC: $FEATURE_SPEC" - echo "IMPL_PLAN: $IMPL_PLAN" - echo "SPECS_DIR: $FEATURE_DIR" - echo "BRANCH: $CURRENT_BRANCH" - echo "HAS_GIT: $HAS_GIT" -fi - diff --git a/.specify/scripts/bash/update-agent-context.sh b/.specify/scripts/bash/update-agent-context.sh deleted file mode 100644 index 6d3e0b3..0000000 --- a/.specify/scripts/bash/update-agent-context.sh +++ /dev/null @@ -1,799 +0,0 @@ -#!/usr/bin/env bash - -# Update agent context files with information from plan.md -# -# This script maintains AI agent context files by parsing feature specifications -# and updating agent-specific configuration files with project information. -# -# MAIN FUNCTIONS: -# 1. Environment Validation -# - Verifies git repository structure and branch information -# - Checks for required plan.md files and templates -# - Validates file permissions and accessibility -# -# 2. Plan Data Extraction -# - Parses plan.md files to extract project metadata -# - Identifies language/version, frameworks, databases, and project types -# - Handles missing or incomplete specification data gracefully -# -# 3. Agent File Management -# - Creates new agent context files from templates when needed -# - Updates existing agent files with new project information -# - Preserves manual additions and custom configurations -# - Supports multiple AI agent formats and directory structures -# -# 4. Content Generation -# - Generates language-specific build/test commands -# - Creates appropriate project directory structures -# - Updates technology stacks and recent changes sections -# - Maintains consistent formatting and timestamps -# -# 5. Multi-Agent Support -# - Handles agent-specific file paths and naming conventions -# - Supports: Claude, Gemini, Copilot, Cursor, Qwen, opencode, Codex, Windsurf, Kilo Code, Auggie CLI, Roo Code, CodeBuddy CLI, Qoder CLI, Amp, SHAI, or Amazon Q Developer CLI -# - Can update single agents or all existing agent files -# - Creates default Claude file if no agent files exist -# -# Usage: ./update-agent-context.sh [agent_type] -# Agent types: claude|gemini|copilot|cursor-agent|qwen|opencode|codex|windsurf|kilocode|auggie|shai|q|bob|qoder -# Leave empty to update all existing agent files - -set -e - -# Enable strict error handling -set -u -set -o pipefail - -#============================================================================== -# Configuration and Global Variables -#============================================================================== - -# Get script directory and load common functions -SCRIPT_DIR="$(CDPATH="" cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)" -source "$SCRIPT_DIR/common.sh" - -# Get all paths and variables from common functions -eval $(get_feature_paths) - -NEW_PLAN="$IMPL_PLAN" # Alias for compatibility with existing code -AGENT_TYPE="${1:-}" - -# Agent-specific file paths -CLAUDE_FILE="$REPO_ROOT/CLAUDE.md" -GEMINI_FILE="$REPO_ROOT/GEMINI.md" -COPILOT_FILE="$REPO_ROOT/.github/agents/copilot-instructions.md" -CURSOR_FILE="$REPO_ROOT/.cursor/rules/specify-rules.mdc" -QWEN_FILE="$REPO_ROOT/QWEN.md" -AGENTS_FILE="$REPO_ROOT/AGENTS.md" -WINDSURF_FILE="$REPO_ROOT/.windsurf/rules/specify-rules.md" -KILOCODE_FILE="$REPO_ROOT/.kilocode/rules/specify-rules.md" -AUGGIE_FILE="$REPO_ROOT/.augment/rules/specify-rules.md" -ROO_FILE="$REPO_ROOT/.roo/rules/specify-rules.md" -CODEBUDDY_FILE="$REPO_ROOT/CODEBUDDY.md" -QODER_FILE="$REPO_ROOT/QODER.md" -AMP_FILE="$REPO_ROOT/AGENTS.md" -SHAI_FILE="$REPO_ROOT/SHAI.md" -Q_FILE="$REPO_ROOT/AGENTS.md" -BOB_FILE="$REPO_ROOT/AGENTS.md" - -# Template file -TEMPLATE_FILE="$REPO_ROOT/.specify/templates/agent-file-template.md" - -# Global variables for parsed plan data -NEW_LANG="" -NEW_FRAMEWORK="" -NEW_DB="" -NEW_PROJECT_TYPE="" - -#============================================================================== -# Utility Functions -#============================================================================== - -log_info() { - echo "INFO: $1" -} - -log_success() { - echo "✓ $1" -} - -log_error() { - echo "ERROR: $1" >&2 -} - -log_warning() { - echo "WARNING: $1" >&2 -} - -# Cleanup function for temporary files -cleanup() { - local exit_code=$? - rm -f /tmp/agent_update_*_$$ - rm -f /tmp/manual_additions_$$ - exit $exit_code -} - -# Set up cleanup trap -trap cleanup EXIT INT TERM - -#============================================================================== -# Validation Functions -#============================================================================== - -validate_environment() { - # Check if we have a current branch/feature (git or non-git) - if [[ -z "$CURRENT_BRANCH" ]]; then - log_error "Unable to determine current feature" - if [[ "$HAS_GIT" == "true" ]]; then - log_info "Make sure you're on a feature branch" - else - log_info "Set SPECIFY_FEATURE environment variable or create a feature first" - fi - exit 1 - fi - - # Check if plan.md exists - if [[ ! -f "$NEW_PLAN" ]]; then - log_error "No plan.md found at $NEW_PLAN" - log_info "Make sure you're working on a feature with a corresponding spec directory" - if [[ "$HAS_GIT" != "true" ]]; then - log_info "Use: export SPECIFY_FEATURE=your-feature-name or create a new feature first" - fi - exit 1 - fi - - # Check if template exists (needed for new files) - if [[ ! -f "$TEMPLATE_FILE" ]]; then - log_warning "Template file not found at $TEMPLATE_FILE" - log_warning "Creating new agent files will fail" - fi -} - -#============================================================================== -# Plan Parsing Functions -#============================================================================== - -extract_plan_field() { - local field_pattern="$1" - local plan_file="$2" - - grep "^\*\*${field_pattern}\*\*: " "$plan_file" 2>/dev/null | \ - head -1 | \ - sed "s|^\*\*${field_pattern}\*\*: ||" | \ - sed 's/^[ \t]*//;s/[ \t]*$//' | \ - grep -v "NEEDS CLARIFICATION" | \ - grep -v "^N/A$" || echo "" -} - -parse_plan_data() { - local plan_file="$1" - - if [[ ! -f "$plan_file" ]]; then - log_error "Plan file not found: $plan_file" - return 1 - fi - - if [[ ! -r "$plan_file" ]]; then - log_error "Plan file is not readable: $plan_file" - return 1 - fi - - log_info "Parsing plan data from $plan_file" - - NEW_LANG=$(extract_plan_field "Language/Version" "$plan_file") - NEW_FRAMEWORK=$(extract_plan_field "Primary Dependencies" "$plan_file") - NEW_DB=$(extract_plan_field "Storage" "$plan_file") - NEW_PROJECT_TYPE=$(extract_plan_field "Project Type" "$plan_file") - - # Log what we found - if [[ -n "$NEW_LANG" ]]; then - log_info "Found language: $NEW_LANG" - else - log_warning "No language information found in plan" - fi - - if [[ -n "$NEW_FRAMEWORK" ]]; then - log_info "Found framework: $NEW_FRAMEWORK" - fi - - if [[ -n "$NEW_DB" ]] && [[ "$NEW_DB" != "N/A" ]]; then - log_info "Found database: $NEW_DB" - fi - - if [[ -n "$NEW_PROJECT_TYPE" ]]; then - log_info "Found project type: $NEW_PROJECT_TYPE" - fi -} - -format_technology_stack() { - local lang="$1" - local framework="$2" - local parts=() - - # Add non-empty parts - [[ -n "$lang" && "$lang" != "NEEDS CLARIFICATION" ]] && parts+=("$lang") - [[ -n "$framework" && "$framework" != "NEEDS CLARIFICATION" && "$framework" != "N/A" ]] && parts+=("$framework") - - # Join with proper formatting - if [[ ${#parts[@]} -eq 0 ]]; then - echo "" - elif [[ ${#parts[@]} -eq 1 ]]; then - echo "${parts[0]}" - else - # Join multiple parts with " + " - local result="${parts[0]}" - for ((i=1; i<${#parts[@]}; i++)); do - result="$result + ${parts[i]}" - done - echo "$result" - fi -} - -#============================================================================== -# Template and Content Generation Functions -#============================================================================== - -get_project_structure() { - local project_type="$1" - - if [[ "$project_type" == *"web"* ]]; then - echo "backend/\\nfrontend/\\ntests/" - else - echo "src/\\ntests/" - fi -} - -get_commands_for_language() { - local lang="$1" - - case "$lang" in - *"Python"*) - echo "cd src && pytest && ruff check ." - ;; - *"Rust"*) - echo "cargo test && cargo clippy" - ;; - *"JavaScript"*|*"TypeScript"*) - echo "npm test \\&\\& npm run lint" - ;; - *) - echo "# Add commands for $lang" - ;; - esac -} - -get_language_conventions() { - local lang="$1" - echo "$lang: Follow standard conventions" -} - -create_new_agent_file() { - local target_file="$1" - local temp_file="$2" - local project_name="$3" - local current_date="$4" - - if [[ ! -f "$TEMPLATE_FILE" ]]; then - log_error "Template not found at $TEMPLATE_FILE" - return 1 - fi - - if [[ ! -r "$TEMPLATE_FILE" ]]; then - log_error "Template file is not readable: $TEMPLATE_FILE" - return 1 - fi - - log_info "Creating new agent context file from template..." - - if ! cp "$TEMPLATE_FILE" "$temp_file"; then - log_error "Failed to copy template file" - return 1 - fi - - # Replace template placeholders - local project_structure - project_structure=$(get_project_structure "$NEW_PROJECT_TYPE") - - local commands - commands=$(get_commands_for_language "$NEW_LANG") - - local language_conventions - language_conventions=$(get_language_conventions "$NEW_LANG") - - # Perform substitutions with error checking using safer approach - # Escape special characters for sed by using a different delimiter or escaping - local escaped_lang=$(printf '%s\n' "$NEW_LANG" | sed 's/[\[\.*^$()+{}|]/\\&/g') - local escaped_framework=$(printf '%s\n' "$NEW_FRAMEWORK" | sed 's/[\[\.*^$()+{}|]/\\&/g') - local escaped_branch=$(printf '%s\n' "$CURRENT_BRANCH" | sed 's/[\[\.*^$()+{}|]/\\&/g') - - # Build technology stack and recent change strings conditionally - local tech_stack - if [[ -n "$escaped_lang" && -n "$escaped_framework" ]]; then - tech_stack="- $escaped_lang + $escaped_framework ($escaped_branch)" - elif [[ -n "$escaped_lang" ]]; then - tech_stack="- $escaped_lang ($escaped_branch)" - elif [[ -n "$escaped_framework" ]]; then - tech_stack="- $escaped_framework ($escaped_branch)" - else - tech_stack="- ($escaped_branch)" - fi - - local recent_change - if [[ -n "$escaped_lang" && -n "$escaped_framework" ]]; then - recent_change="- $escaped_branch: Added $escaped_lang + $escaped_framework" - elif [[ -n "$escaped_lang" ]]; then - recent_change="- $escaped_branch: Added $escaped_lang" - elif [[ -n "$escaped_framework" ]]; then - recent_change="- $escaped_branch: Added $escaped_framework" - else - recent_change="- $escaped_branch: Added" - fi - - local substitutions=( - "s|\[PROJECT NAME\]|$project_name|" - "s|\[DATE\]|$current_date|" - "s|\[EXTRACTED FROM ALL PLAN.MD FILES\]|$tech_stack|" - "s|\[ACTUAL STRUCTURE FROM PLANS\]|$project_structure|g" - "s|\[ONLY COMMANDS FOR ACTIVE TECHNOLOGIES\]|$commands|" - "s|\[LANGUAGE-SPECIFIC, ONLY FOR LANGUAGES IN USE\]|$language_conventions|" - "s|\[LAST 3 FEATURES AND WHAT THEY ADDED\]|$recent_change|" - ) - - for substitution in "${substitutions[@]}"; do - if ! sed -i.bak -e "$substitution" "$temp_file"; then - log_error "Failed to perform substitution: $substitution" - rm -f "$temp_file" "$temp_file.bak" - return 1 - fi - done - - # Convert \n sequences to actual newlines - newline=$(printf '\n') - sed -i.bak2 "s/\\\\n/${newline}/g" "$temp_file" - - # Clean up backup files - rm -f "$temp_file.bak" "$temp_file.bak2" - - return 0 -} - - - - -update_existing_agent_file() { - local target_file="$1" - local current_date="$2" - - log_info "Updating existing agent context file..." - - # Use a single temporary file for atomic update - local temp_file - temp_file=$(mktemp) || { - log_error "Failed to create temporary file" - return 1 - } - - # Process the file in one pass - local tech_stack=$(format_technology_stack "$NEW_LANG" "$NEW_FRAMEWORK") - local new_tech_entries=() - local new_change_entry="" - - # Prepare new technology entries - if [[ -n "$tech_stack" ]] && ! grep -q "$tech_stack" "$target_file"; then - new_tech_entries+=("- $tech_stack ($CURRENT_BRANCH)") - fi - - if [[ -n "$NEW_DB" ]] && [[ "$NEW_DB" != "N/A" ]] && [[ "$NEW_DB" != "NEEDS CLARIFICATION" ]] && ! grep -q "$NEW_DB" "$target_file"; then - new_tech_entries+=("- $NEW_DB ($CURRENT_BRANCH)") - fi - - # Prepare new change entry - if [[ -n "$tech_stack" ]]; then - new_change_entry="- $CURRENT_BRANCH: Added $tech_stack" - elif [[ -n "$NEW_DB" ]] && [[ "$NEW_DB" != "N/A" ]] && [[ "$NEW_DB" != "NEEDS CLARIFICATION" ]]; then - new_change_entry="- $CURRENT_BRANCH: Added $NEW_DB" - fi - - # Check if sections exist in the file - local has_active_technologies=0 - local has_recent_changes=0 - - if grep -q "^## Active Technologies" "$target_file" 2>/dev/null; then - has_active_technologies=1 - fi - - if grep -q "^## Recent Changes" "$target_file" 2>/dev/null; then - has_recent_changes=1 - fi - - # Process file line by line - local in_tech_section=false - local in_changes_section=false - local tech_entries_added=false - local changes_entries_added=false - local existing_changes_count=0 - local file_ended=false - - while IFS= read -r line || [[ -n "$line" ]]; do - # Handle Active Technologies section - if [[ "$line" == "## Active Technologies" ]]; then - echo "$line" >> "$temp_file" - in_tech_section=true - continue - elif [[ $in_tech_section == true ]] && [[ "$line" =~ ^##[[:space:]] ]]; then - # Add new tech entries before closing the section - if [[ $tech_entries_added == false ]] && [[ ${#new_tech_entries[@]} -gt 0 ]]; then - printf '%s\n' "${new_tech_entries[@]}" >> "$temp_file" - tech_entries_added=true - fi - echo "$line" >> "$temp_file" - in_tech_section=false - continue - elif [[ $in_tech_section == true ]] && [[ -z "$line" ]]; then - # Add new tech entries before empty line in tech section - if [[ $tech_entries_added == false ]] && [[ ${#new_tech_entries[@]} -gt 0 ]]; then - printf '%s\n' "${new_tech_entries[@]}" >> "$temp_file" - tech_entries_added=true - fi - echo "$line" >> "$temp_file" - continue - fi - - # Handle Recent Changes section - if [[ "$line" == "## Recent Changes" ]]; then - echo "$line" >> "$temp_file" - # Add new change entry right after the heading - if [[ -n "$new_change_entry" ]]; then - echo "$new_change_entry" >> "$temp_file" - fi - in_changes_section=true - changes_entries_added=true - continue - elif [[ $in_changes_section == true ]] && [[ "$line" =~ ^##[[:space:]] ]]; then - echo "$line" >> "$temp_file" - in_changes_section=false - continue - elif [[ $in_changes_section == true ]] && [[ "$line" == "- "* ]]; then - # Keep only first 2 existing changes - if [[ $existing_changes_count -lt 2 ]]; then - echo "$line" >> "$temp_file" - ((existing_changes_count++)) - fi - continue - fi - - # Update timestamp - if [[ "$line" =~ \*\*Last\ updated\*\*:.*[0-9][0-9][0-9][0-9]-[0-9][0-9]-[0-9][0-9] ]]; then - echo "$line" | sed "s/[0-9][0-9][0-9][0-9]-[0-9][0-9]-[0-9][0-9]/$current_date/" >> "$temp_file" - else - echo "$line" >> "$temp_file" - fi - done < "$target_file" - - # Post-loop check: if we're still in the Active Technologies section and haven't added new entries - if [[ $in_tech_section == true ]] && [[ $tech_entries_added == false ]] && [[ ${#new_tech_entries[@]} -gt 0 ]]; then - printf '%s\n' "${new_tech_entries[@]}" >> "$temp_file" - tech_entries_added=true - fi - - # If sections don't exist, add them at the end of the file - if [[ $has_active_technologies -eq 0 ]] && [[ ${#new_tech_entries[@]} -gt 0 ]]; then - echo "" >> "$temp_file" - echo "## Active Technologies" >> "$temp_file" - printf '%s\n' "${new_tech_entries[@]}" >> "$temp_file" - tech_entries_added=true - fi - - if [[ $has_recent_changes -eq 0 ]] && [[ -n "$new_change_entry" ]]; then - echo "" >> "$temp_file" - echo "## Recent Changes" >> "$temp_file" - echo "$new_change_entry" >> "$temp_file" - changes_entries_added=true - fi - - # Move temp file to target atomically - if ! mv "$temp_file" "$target_file"; then - log_error "Failed to update target file" - rm -f "$temp_file" - return 1 - fi - - return 0 -} -#============================================================================== -# Main Agent File Update Function -#============================================================================== - -update_agent_file() { - local target_file="$1" - local agent_name="$2" - - if [[ -z "$target_file" ]] || [[ -z "$agent_name" ]]; then - log_error "update_agent_file requires target_file and agent_name parameters" - return 1 - fi - - log_info "Updating $agent_name context file: $target_file" - - local project_name - project_name=$(basename "$REPO_ROOT") - local current_date - current_date=$(date +%Y-%m-%d) - - # Create directory if it doesn't exist - local target_dir - target_dir=$(dirname "$target_file") - if [[ ! -d "$target_dir" ]]; then - if ! mkdir -p "$target_dir"; then - log_error "Failed to create directory: $target_dir" - return 1 - fi - fi - - if [[ ! -f "$target_file" ]]; then - # Create new file from template - local temp_file - temp_file=$(mktemp) || { - log_error "Failed to create temporary file" - return 1 - } - - if create_new_agent_file "$target_file" "$temp_file" "$project_name" "$current_date"; then - if mv "$temp_file" "$target_file"; then - log_success "Created new $agent_name context file" - else - log_error "Failed to move temporary file to $target_file" - rm -f "$temp_file" - return 1 - fi - else - log_error "Failed to create new agent file" - rm -f "$temp_file" - return 1 - fi - else - # Update existing file - if [[ ! -r "$target_file" ]]; then - log_error "Cannot read existing file: $target_file" - return 1 - fi - - if [[ ! -w "$target_file" ]]; then - log_error "Cannot write to existing file: $target_file" - return 1 - fi - - if update_existing_agent_file "$target_file" "$current_date"; then - log_success "Updated existing $agent_name context file" - else - log_error "Failed to update existing agent file" - return 1 - fi - fi - - return 0 -} - -#============================================================================== -# Agent Selection and Processing -#============================================================================== - -update_specific_agent() { - local agent_type="$1" - - case "$agent_type" in - claude) - update_agent_file "$CLAUDE_FILE" "Claude Code" - ;; - gemini) - update_agent_file "$GEMINI_FILE" "Gemini CLI" - ;; - copilot) - update_agent_file "$COPILOT_FILE" "GitHub Copilot" - ;; - cursor-agent) - update_agent_file "$CURSOR_FILE" "Cursor IDE" - ;; - qwen) - update_agent_file "$QWEN_FILE" "Qwen Code" - ;; - opencode) - update_agent_file "$AGENTS_FILE" "opencode" - ;; - codex) - update_agent_file "$AGENTS_FILE" "Codex CLI" - ;; - windsurf) - update_agent_file "$WINDSURF_FILE" "Windsurf" - ;; - kilocode) - update_agent_file "$KILOCODE_FILE" "Kilo Code" - ;; - auggie) - update_agent_file "$AUGGIE_FILE" "Auggie CLI" - ;; - roo) - update_agent_file "$ROO_FILE" "Roo Code" - ;; - codebuddy) - update_agent_file "$CODEBUDDY_FILE" "CodeBuddy CLI" - ;; - qoder) - update_agent_file "$QODER_FILE" "Qoder CLI" - ;; - amp) - update_agent_file "$AMP_FILE" "Amp" - ;; - shai) - update_agent_file "$SHAI_FILE" "SHAI" - ;; - q) - update_agent_file "$Q_FILE" "Amazon Q Developer CLI" - ;; - bob) - update_agent_file "$BOB_FILE" "IBM Bob" - ;; - *) - log_error "Unknown agent type '$agent_type'" - log_error "Expected: claude|gemini|copilot|cursor-agent|qwen|opencode|codex|windsurf|kilocode|auggie|roo|amp|shai|q|bob|qoder" - exit 1 - ;; - esac -} - -update_all_existing_agents() { - local found_agent=false - - # Check each possible agent file and update if it exists - if [[ -f "$CLAUDE_FILE" ]]; then - update_agent_file "$CLAUDE_FILE" "Claude Code" - found_agent=true - fi - - if [[ -f "$GEMINI_FILE" ]]; then - update_agent_file "$GEMINI_FILE" "Gemini CLI" - found_agent=true - fi - - if [[ -f "$COPILOT_FILE" ]]; then - update_agent_file "$COPILOT_FILE" "GitHub Copilot" - found_agent=true - fi - - if [[ -f "$CURSOR_FILE" ]]; then - update_agent_file "$CURSOR_FILE" "Cursor IDE" - found_agent=true - fi - - if [[ -f "$QWEN_FILE" ]]; then - update_agent_file "$QWEN_FILE" "Qwen Code" - found_agent=true - fi - - if [[ -f "$AGENTS_FILE" ]]; then - update_agent_file "$AGENTS_FILE" "Codex/opencode" - found_agent=true - fi - - if [[ -f "$WINDSURF_FILE" ]]; then - update_agent_file "$WINDSURF_FILE" "Windsurf" - found_agent=true - fi - - if [[ -f "$KILOCODE_FILE" ]]; then - update_agent_file "$KILOCODE_FILE" "Kilo Code" - found_agent=true - fi - - if [[ -f "$AUGGIE_FILE" ]]; then - update_agent_file "$AUGGIE_FILE" "Auggie CLI" - found_agent=true - fi - - if [[ -f "$ROO_FILE" ]]; then - update_agent_file "$ROO_FILE" "Roo Code" - found_agent=true - fi - - if [[ -f "$CODEBUDDY_FILE" ]]; then - update_agent_file "$CODEBUDDY_FILE" "CodeBuddy CLI" - found_agent=true - fi - - if [[ -f "$SHAI_FILE" ]]; then - update_agent_file "$SHAI_FILE" "SHAI" - found_agent=true - fi - - if [[ -f "$QODER_FILE" ]]; then - update_agent_file "$QODER_FILE" "Qoder CLI" - found_agent=true - fi - - if [[ -f "$Q_FILE" ]]; then - update_agent_file "$Q_FILE" "Amazon Q Developer CLI" - found_agent=true - fi - - if [[ -f "$BOB_FILE" ]]; then - update_agent_file "$BOB_FILE" "IBM Bob" - found_agent=true - fi - - # If no agent files exist, create a default Claude file - if [[ "$found_agent" == false ]]; then - log_info "No existing agent files found, creating default Claude file..." - update_agent_file "$CLAUDE_FILE" "Claude Code" - fi -} -print_summary() { - echo - log_info "Summary of changes:" - - if [[ -n "$NEW_LANG" ]]; then - echo " - Added language: $NEW_LANG" - fi - - if [[ -n "$NEW_FRAMEWORK" ]]; then - echo " - Added framework: $NEW_FRAMEWORK" - fi - - if [[ -n "$NEW_DB" ]] && [[ "$NEW_DB" != "N/A" ]]; then - echo " - Added database: $NEW_DB" - fi - - echo - - log_info "Usage: $0 [claude|gemini|copilot|cursor-agent|qwen|opencode|codex|windsurf|kilocode|auggie|codebuddy|shai|q|bob|qoder]" -} - -#============================================================================== -# Main Execution -#============================================================================== - -main() { - # Validate environment before proceeding - validate_environment - - log_info "=== Updating agent context files for feature $CURRENT_BRANCH ===" - - # Parse the plan file to extract project information - if ! parse_plan_data "$NEW_PLAN"; then - log_error "Failed to parse plan data" - exit 1 - fi - - # Process based on agent type argument - local success=true - - if [[ -z "$AGENT_TYPE" ]]; then - # No specific agent provided - update all existing agent files - log_info "No agent specified, updating all existing agent files..." - if ! update_all_existing_agents; then - success=false - fi - else - # Specific agent provided - update only that agent - log_info "Updating specific agent: $AGENT_TYPE" - if ! update_specific_agent "$AGENT_TYPE"; then - success=false - fi - fi - - # Print summary - print_summary - - if [[ "$success" == true ]]; then - log_success "Agent context update completed successfully" - exit 0 - else - log_error "Agent context update completed with errors" - exit 1 - fi -} - -# Execute main function if script is run directly -if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then - main "$@" -fi - diff --git a/.specify/templates/adr-template.md b/.specify/templates/adr-template.md deleted file mode 100644 index b4cd4ca..0000000 --- a/.specify/templates/adr-template.md +++ /dev/null @@ -1,56 +0,0 @@ -# ADR-{{ID}}: {{TITLE}} - -> **Scope**: Document decision clusters, not individual technology choices. Group related decisions that work together (e.g., "Frontend Stack" not separate ADRs for framework, styling, deployment). - -- **Status:** Proposed | Accepted | Superseded | Rejected -- **Date:** {{DATE_ISO}} -- **Feature:** {{FEATURE_NAME}} -- **Context:** {{CONTEXT}} - -<!-- Significance checklist (ALL must be true to justify this ADR) - 1) Impact: Long-term consequence for architecture/platform/security? - 2) Alternatives: Multiple viable options considered with tradeoffs? - 3) Scope: Cross-cutting concern (not an isolated detail)? - If any are false, prefer capturing as a PHR note instead of an ADR. --> - -## Decision - -{{DECISION}} - -<!-- For technology stacks, list all components: - - Framework: Next.js 14 (App Router) - - Styling: Tailwind CSS v3 - - Deployment: Vercel - - State Management: React Context (start simple) ---> - -## Consequences - -### Positive - -{{POSITIVE_CONSEQUENCES}} - -<!-- Example: Integrated tooling, excellent DX, fast deploys, strong TypeScript support --> - -### Negative - -{{NEGATIVE_CONSEQUENCES}} - -<!-- Example: Vendor lock-in to Vercel, framework coupling, learning curve --> - -## Alternatives Considered - -{{ALTERNATIVES}} - -<!-- Group alternatives by cluster: - Alternative Stack A: Remix + styled-components + Cloudflare - Alternative Stack B: Vite + vanilla CSS + AWS Amplify - Why rejected: Less integrated, more setup complexity ---> - -## References - -- Feature Spec: {{SPEC_LINK}} -- Implementation Plan: {{PLAN_LINK}} -- Related ADRs: {{RELATED_ADRS}} -- Evaluator Evidence: {{EVAL_NOTES_LINK}} <!-- link to eval notes/PHR showing graders and outcomes --> diff --git a/.specify/templates/agent-file-template.md b/.specify/templates/agent-file-template.md deleted file mode 100644 index 4cc7fd6..0000000 --- a/.specify/templates/agent-file-template.md +++ /dev/null @@ -1,28 +0,0 @@ -# [PROJECT NAME] Development Guidelines - -Auto-generated from all feature plans. Last updated: [DATE] - -## Active Technologies - -[EXTRACTED FROM ALL PLAN.MD FILES] - -## Project Structure - -```text -[ACTUAL STRUCTURE FROM PLANS] -``` - -## Commands - -[ONLY COMMANDS FOR ACTIVE TECHNOLOGIES] - -## Code Style - -[LANGUAGE-SPECIFIC, ONLY FOR LANGUAGES IN USE] - -## Recent Changes - -[LAST 3 FEATURES AND WHAT THEY ADDED] - -<!-- MANUAL ADDITIONS START --> -<!-- MANUAL ADDITIONS END --> diff --git a/.specify/templates/checklist-template.md b/.specify/templates/checklist-template.md deleted file mode 100644 index 87a4295..0000000 --- a/.specify/templates/checklist-template.md +++ /dev/null @@ -1,40 +0,0 @@ -# [CHECKLIST TYPE] Checklist: [FEATURE NAME] - -**Purpose**: [Brief description of what this checklist covers] -**Created**: [DATE] -**Feature**: [Link to spec.md or relevant documentation] - -**Note**: This checklist is generated by the `/sp.checklist` command based on feature context and requirements. - -<!-- - ============================================================================ - IMPORTANT: The checklist items below are SAMPLE ITEMS for illustration only. - - The /sp.checklist command MUST replace these with actual items based on: - - User's specific checklist request - - Feature requirements from spec.md - - Technical context from plan.md - - Implementation details from tasks.md - - DO NOT keep these sample items in the generated checklist file. - ============================================================================ ---> - -## [Category 1] - -- [ ] CHK001 First checklist item with clear action -- [ ] CHK002 Second checklist item -- [ ] CHK003 Third checklist item - -## [Category 2] - -- [ ] CHK004 Another category item -- [ ] CHK005 Item with specific criteria -- [ ] CHK006 Final item in this category - -## Notes - -- Check items off as completed: `[x]` -- Add comments or findings inline -- Link to relevant resources or documentation -- Items are numbered sequentially for easy reference diff --git a/.specify/templates/phr-template.prompt.md b/.specify/templates/phr-template.prompt.md deleted file mode 100644 index 3315d8e..0000000 --- a/.specify/templates/phr-template.prompt.md +++ /dev/null @@ -1,45 +0,0 @@ ---- -id: {{ID}} -title: {{TITLE}} -stage: {{STAGE}} -date: {{DATE_ISO}} -surface: {{SURFACE}} -model: {{MODEL}} -feature: {{FEATURE}} -branch: {{BRANCH}} -user: {{USER}} -command: {{COMMAND}} -labels: [{{LABELS}}] -links: - spec: {{LINKS_SPEC}} - ticket: {{LINKS_TICKET}} - adr: {{LINKS_ADR}} - pr: {{LINKS_PR}} -files: -{{FILES_YAML}} -tests: -{{TESTS_YAML}} ---- - -## Prompt - -{{PROMPT_TEXT}} - -## Response snapshot - -{{RESPONSE_TEXT}} - -## Outcome - -- ✅ Impact: {{OUTCOME_IMPACT}} -- 🧪 Tests: {{TESTS_SUMMARY}} -- 📁 Files: {{FILES_SUMMARY}} -- 🔁 Next prompts: {{NEXT_PROMPTS}} -- 🧠 Reflection: {{REFLECTION_NOTE}} - -## Evaluation notes (flywheel) - -- Failure modes observed: {{FAILURE_MODES}} -- Graders run and results (PASS/FAIL): {{GRADER_RESULTS}} -- Prompt variant (if applicable): {{PROMPT_VARIANT_ID}} -- Next experiment (smallest change to try): {{NEXT_EXPERIMENT}} diff --git a/.specify/templates/plan-template.md b/.specify/templates/plan-template.md deleted file mode 100644 index b420402..0000000 --- a/.specify/templates/plan-template.md +++ /dev/null @@ -1,104 +0,0 @@ -# Implementation Plan: [FEATURE] - -**Branch**: `[###-feature-name]` | **Date**: [DATE] | **Spec**: [link] -**Input**: Feature specification from `/specs/[###-feature-name]/spec.md` - -**Note**: This template is filled in by the `/sp.plan` command. See `.specify/templates/commands/plan.md` for the execution workflow. - -## Summary - -[Extract from feature spec: primary requirement + technical approach from research] - -## Technical Context - -<!-- - ACTION REQUIRED: Replace the content in this section with the technical details - for the project. The structure here is presented in advisory capacity to guide - the iteration process. ---> - -**Language/Version**: [e.g., Python 3.11, Swift 5.9, Rust 1.75 or NEEDS CLARIFICATION] -**Primary Dependencies**: [e.g., FastAPI, UIKit, LLVM or NEEDS CLARIFICATION] -**Storage**: [if applicable, e.g., PostgreSQL, CoreData, files or N/A] -**Testing**: [e.g., pytest, XCTest, cargo test or NEEDS CLARIFICATION] -**Target Platform**: [e.g., Linux server, iOS 15+, WASM or NEEDS CLARIFICATION] -**Project Type**: [single/web/mobile - determines source structure] -**Performance Goals**: [domain-specific, e.g., 1000 req/s, 10k lines/sec, 60 fps or NEEDS CLARIFICATION] -**Constraints**: [domain-specific, e.g., <200ms p95, <100MB memory, offline-capable or NEEDS CLARIFICATION] -**Scale/Scope**: [domain-specific, e.g., 10k users, 1M LOC, 50 screens or NEEDS CLARIFICATION] - -## Constitution Check - -*GATE: Must pass before Phase 0 research. Re-check after Phase 1 design.* - -[Gates determined based on constitution file] - -## Project Structure - -### Documentation (this feature) - -```text -specs/[###-feature]/ -├── plan.md # This file (/sp.plan command output) -├── research.md # Phase 0 output (/sp.plan command) -├── data-model.md # Phase 1 output (/sp.plan command) -├── quickstart.md # Phase 1 output (/sp.plan command) -├── contracts/ # Phase 1 output (/sp.plan command) -└── tasks.md # Phase 2 output (/sp.tasks command - NOT created by /sp.plan) -``` - -### Source Code (repository root) -<!-- - ACTION REQUIRED: Replace the placeholder tree below with the concrete layout - for this feature. Delete unused options and expand the chosen structure with - real paths (e.g., apps/admin, packages/something). The delivered plan must - not include Option labels. ---> - -```text -# [REMOVE IF UNUSED] Option 1: Single project (DEFAULT) -src/ -├── models/ -├── services/ -├── cli/ -└── lib/ - -tests/ -├── contract/ -├── integration/ -└── unit/ - -# [REMOVE IF UNUSED] Option 2: Web application (when "frontend" + "backend" detected) -backend/ -├── src/ -│ ├── models/ -│ ├── services/ -│ └── api/ -└── tests/ - -frontend/ -├── src/ -│ ├── components/ -│ ├── pages/ -│ └── services/ -└── tests/ - -# [REMOVE IF UNUSED] Option 3: Mobile + API (when "iOS/Android" detected) -api/ -└── [same as backend above] - -ios/ or android/ -└── [platform-specific structure: feature modules, UI flows, platform tests] -``` - -**Structure Decision**: [Document the selected structure and reference the real -directories captured above] - -## Complexity Tracking - -> **Fill ONLY if Constitution Check has violations that must be justified** - -| Violation | Why Needed | Simpler Alternative Rejected Because | -|-----------|------------|-------------------------------------| -| [e.g., 4th project] | [current need] | [why 3 projects insufficient] | -| [e.g., Repository pattern] | [specific problem] | [why direct DB access insufficient] | diff --git a/.specify/templates/spec-template.md b/.specify/templates/spec-template.md deleted file mode 100644 index c67d914..0000000 --- a/.specify/templates/spec-template.md +++ /dev/null @@ -1,115 +0,0 @@ -# Feature Specification: [FEATURE NAME] - -**Feature Branch**: `[###-feature-name]` -**Created**: [DATE] -**Status**: Draft -**Input**: User description: "$ARGUMENTS" - -## User Scenarios & Testing *(mandatory)* - -<!-- - IMPORTANT: User stories should be PRIORITIZED as user journeys ordered by importance. - Each user story/journey must be INDEPENDENTLY TESTABLE - meaning if you implement just ONE of them, - you should still have a viable MVP (Minimum Viable Product) that delivers value. - - Assign priorities (P1, P2, P3, etc.) to each story, where P1 is the most critical. - Think of each story as a standalone slice of functionality that can be: - - Developed independently - - Tested independently - - Deployed independently - - Demonstrated to users independently ---> - -### User Story 1 - [Brief Title] (Priority: P1) - -[Describe this user journey in plain language] - -**Why this priority**: [Explain the value and why it has this priority level] - -**Independent Test**: [Describe how this can be tested independently - e.g., "Can be fully tested by [specific action] and delivers [specific value]"] - -**Acceptance Scenarios**: - -1. **Given** [initial state], **When** [action], **Then** [expected outcome] -2. **Given** [initial state], **When** [action], **Then** [expected outcome] - ---- - -### User Story 2 - [Brief Title] (Priority: P2) - -[Describe this user journey in plain language] - -**Why this priority**: [Explain the value and why it has this priority level] - -**Independent Test**: [Describe how this can be tested independently] - -**Acceptance Scenarios**: - -1. **Given** [initial state], **When** [action], **Then** [expected outcome] - ---- - -### User Story 3 - [Brief Title] (Priority: P3) - -[Describe this user journey in plain language] - -**Why this priority**: [Explain the value and why it has this priority level] - -**Independent Test**: [Describe how this can be tested independently] - -**Acceptance Scenarios**: - -1. **Given** [initial state], **When** [action], **Then** [expected outcome] - ---- - -[Add more user stories as needed, each with an assigned priority] - -### Edge Cases - -<!-- - ACTION REQUIRED: The content in this section represents placeholders. - Fill them out with the right edge cases. ---> - -- What happens when [boundary condition]? -- How does system handle [error scenario]? - -## Requirements *(mandatory)* - -<!-- - ACTION REQUIRED: The content in this section represents placeholders. - Fill them out with the right functional requirements. ---> - -### Functional Requirements - -- **FR-001**: System MUST [specific capability, e.g., "allow users to create accounts"] -- **FR-002**: System MUST [specific capability, e.g., "validate email addresses"] -- **FR-003**: Users MUST be able to [key interaction, e.g., "reset their password"] -- **FR-004**: System MUST [data requirement, e.g., "persist user preferences"] -- **FR-005**: System MUST [behavior, e.g., "log all security events"] - -*Example of marking unclear requirements:* - -- **FR-006**: System MUST authenticate users via [NEEDS CLARIFICATION: auth method not specified - email/password, SSO, OAuth?] -- **FR-007**: System MUST retain user data for [NEEDS CLARIFICATION: retention period not specified] - -### Key Entities *(include if feature involves data)* - -- **[Entity 1]**: [What it represents, key attributes without implementation] -- **[Entity 2]**: [What it represents, relationships to other entities] - -## Success Criteria *(mandatory)* - -<!-- - ACTION REQUIRED: Define measurable success criteria. - These must be technology-agnostic and measurable. ---> - -### Measurable Outcomes - -- **SC-001**: [Measurable metric, e.g., "Users can complete account creation in under 2 minutes"] -- **SC-002**: [Measurable metric, e.g., "System handles 1000 concurrent users without degradation"] -- **SC-003**: [User satisfaction metric, e.g., "90% of users successfully complete primary task on first attempt"] -- **SC-004**: [Business metric, e.g., "Reduce support tickets related to [X] by 50%"] diff --git a/.specify/templates/tasks-template.md b/.specify/templates/tasks-template.md deleted file mode 100644 index 978dfcf..0000000 --- a/.specify/templates/tasks-template.md +++ /dev/null @@ -1,251 +0,0 @@ ---- - -description: "Task list template for feature implementation" ---- - -# Tasks: [FEATURE NAME] - -**Input**: Design documents from `/specs/[###-feature-name]/` -**Prerequisites**: plan.md (required), spec.md (required for user stories), research.md, data-model.md, contracts/ - -**Tests**: The examples below include test tasks. Tests are OPTIONAL - only include them if explicitly requested in the feature specification. - -**Organization**: Tasks are grouped by user story to enable independent implementation and testing of each story. - -## Format: `[ID] [P?] [Story] Description` - -- **[P]**: Can run in parallel (different files, no dependencies) -- **[Story]**: Which user story this task belongs to (e.g., US1, US2, US3) -- Include exact file paths in descriptions - -## Path Conventions - -- **Single project**: `src/`, `tests/` at repository root -- **Web app**: `backend/src/`, `frontend/src/` -- **Mobile**: `api/src/`, `ios/src/` or `android/src/` -- Paths shown below assume single project - adjust based on plan.md structure - -<!-- - ============================================================================ - IMPORTANT: The tasks below are SAMPLE TASKS for illustration purposes only. - - The /sp.tasks command MUST replace these with actual tasks based on: - - User stories from spec.md (with their priorities P1, P2, P3...) - - Feature requirements from plan.md - - Entities from data-model.md - - Endpoints from contracts/ - - Tasks MUST be organized by user story so each story can be: - - Implemented independently - - Tested independently - - Delivered as an MVP increment - - DO NOT keep these sample tasks in the generated tasks.md file. - ============================================================================ ---> - -## Phase 1: Setup (Shared Infrastructure) - -**Purpose**: Project initialization and basic structure - -- [ ] T001 Create project structure per implementation plan -- [ ] T002 Initialize [language] project with [framework] dependencies -- [ ] T003 [P] Configure linting and formatting tools - ---- - -## Phase 2: Foundational (Blocking Prerequisites) - -**Purpose**: Core infrastructure that MUST be complete before ANY user story can be implemented - -**⚠️ CRITICAL**: No user story work can begin until this phase is complete - -Examples of foundational tasks (adjust based on your project): - -- [ ] T004 Setup database schema and migrations framework -- [ ] T005 [P] Implement authentication/authorization framework -- [ ] T006 [P] Setup API routing and middleware structure -- [ ] T007 Create base models/entities that all stories depend on -- [ ] T008 Configure error handling and logging infrastructure -- [ ] T009 Setup environment configuration management - -**Checkpoint**: Foundation ready - user story implementation can now begin in parallel - ---- - -## Phase 3: User Story 1 - [Title] (Priority: P1) 🎯 MVP - -**Goal**: [Brief description of what this story delivers] - -**Independent Test**: [How to verify this story works on its own] - -### Tests for User Story 1 (OPTIONAL - only if tests requested) ⚠️ - -> **NOTE: Write these tests FIRST, ensure they FAIL before implementation** - -- [ ] T010 [P] [US1] Contract test for [endpoint] in tests/contract/test_[name].py -- [ ] T011 [P] [US1] Integration test for [user journey] in tests/integration/test_[name].py - -### Implementation for User Story 1 - -- [ ] T012 [P] [US1] Create [Entity1] model in src/models/[entity1].py -- [ ] T013 [P] [US1] Create [Entity2] model in src/models/[entity2].py -- [ ] T014 [US1] Implement [Service] in src/services/[service].py (depends on T012, T013) -- [ ] T015 [US1] Implement [endpoint/feature] in src/[location]/[file].py -- [ ] T016 [US1] Add validation and error handling -- [ ] T017 [US1] Add logging for user story 1 operations - -**Checkpoint**: At this point, User Story 1 should be fully functional and testable independently - ---- - -## Phase 4: User Story 2 - [Title] (Priority: P2) - -**Goal**: [Brief description of what this story delivers] - -**Independent Test**: [How to verify this story works on its own] - -### Tests for User Story 2 (OPTIONAL - only if tests requested) ⚠️ - -- [ ] T018 [P] [US2] Contract test for [endpoint] in tests/contract/test_[name].py -- [ ] T019 [P] [US2] Integration test for [user journey] in tests/integration/test_[name].py - -### Implementation for User Story 2 - -- [ ] T020 [P] [US2] Create [Entity] model in src/models/[entity].py -- [ ] T021 [US2] Implement [Service] in src/services/[service].py -- [ ] T022 [US2] Implement [endpoint/feature] in src/[location]/[file].py -- [ ] T023 [US2] Integrate with User Story 1 components (if needed) - -**Checkpoint**: At this point, User Stories 1 AND 2 should both work independently - ---- - -## Phase 5: User Story 3 - [Title] (Priority: P3) - -**Goal**: [Brief description of what this story delivers] - -**Independent Test**: [How to verify this story works on its own] - -### Tests for User Story 3 (OPTIONAL - only if tests requested) ⚠️ - -- [ ] T024 [P] [US3] Contract test for [endpoint] in tests/contract/test_[name].py -- [ ] T025 [P] [US3] Integration test for [user journey] in tests/integration/test_[name].py - -### Implementation for User Story 3 - -- [ ] T026 [P] [US3] Create [Entity] model in src/models/[entity].py -- [ ] T027 [US3] Implement [Service] in src/services/[service].py -- [ ] T028 [US3] Implement [endpoint/feature] in src/[location]/[file].py - -**Checkpoint**: All user stories should now be independently functional - ---- - -[Add more user story phases as needed, following the same pattern] - ---- - -## Phase N: Polish & Cross-Cutting Concerns - -**Purpose**: Improvements that affect multiple user stories - -- [ ] TXXX [P] Documentation updates in docs/ -- [ ] TXXX Code cleanup and refactoring -- [ ] TXXX Performance optimization across all stories -- [ ] TXXX [P] Additional unit tests (if requested) in tests/unit/ -- [ ] TXXX Security hardening -- [ ] TXXX Run quickstart.md validation - ---- - -## Dependencies & Execution Order - -### Phase Dependencies - -- **Setup (Phase 1)**: No dependencies - can start immediately -- **Foundational (Phase 2)**: Depends on Setup completion - BLOCKS all user stories -- **User Stories (Phase 3+)**: All depend on Foundational phase completion - - User stories can then proceed in parallel (if staffed) - - Or sequentially in priority order (P1 → P2 → P3) -- **Polish (Final Phase)**: Depends on all desired user stories being complete - -### User Story Dependencies - -- **User Story 1 (P1)**: Can start after Foundational (Phase 2) - No dependencies on other stories -- **User Story 2 (P2)**: Can start after Foundational (Phase 2) - May integrate with US1 but should be independently testable -- **User Story 3 (P3)**: Can start after Foundational (Phase 2) - May integrate with US1/US2 but should be independently testable - -### Within Each User Story - -- Tests (if included) MUST be written and FAIL before implementation -- Models before services -- Services before endpoints -- Core implementation before integration -- Story complete before moving to next priority - -### Parallel Opportunities - -- All Setup tasks marked [P] can run in parallel -- All Foundational tasks marked [P] can run in parallel (within Phase 2) -- Once Foundational phase completes, all user stories can start in parallel (if team capacity allows) -- All tests for a user story marked [P] can run in parallel -- Models within a story marked [P] can run in parallel -- Different user stories can be worked on in parallel by different team members - ---- - -## Parallel Example: User Story 1 - -```bash -# Launch all tests for User Story 1 together (if tests requested): -Task: "Contract test for [endpoint] in tests/contract/test_[name].py" -Task: "Integration test for [user journey] in tests/integration/test_[name].py" - -# Launch all models for User Story 1 together: -Task: "Create [Entity1] model in src/models/[entity1].py" -Task: "Create [Entity2] model in src/models/[entity2].py" -``` - ---- - -## Implementation Strategy - -### MVP First (User Story 1 Only) - -1. Complete Phase 1: Setup -2. Complete Phase 2: Foundational (CRITICAL - blocks all stories) -3. Complete Phase 3: User Story 1 -4. **STOP and VALIDATE**: Test User Story 1 independently -5. Deploy/demo if ready - -### Incremental Delivery - -1. Complete Setup + Foundational → Foundation ready -2. Add User Story 1 → Test independently → Deploy/Demo (MVP!) -3. Add User Story 2 → Test independently → Deploy/Demo -4. Add User Story 3 → Test independently → Deploy/Demo -5. Each story adds value without breaking previous stories - -### Parallel Team Strategy - -With multiple developers: - -1. Team completes Setup + Foundational together -2. Once Foundational is done: - - Developer A: User Story 1 - - Developer B: User Story 2 - - Developer C: User Story 3 -3. Stories complete and integrate independently - ---- - -## Notes - -- [P] tasks = different files, no dependencies -- [Story] label maps task to specific user story for traceability -- Each user story should be independently completable and testable -- Verify tests fail before implementing -- Commit after each task or logical group -- Stop at any checkpoint to validate story independently -- Avoid: vague tasks, same file conflicts, cross-story dependencies that break independence diff --git a/CLAUDE.md b/CLAUDE.md deleted file mode 100644 index f26964b..0000000 --- a/CLAUDE.md +++ /dev/null @@ -1,210 +0,0 @@ -# Claude Code Rules - -This file is generated during init for the selected agent. - -You are an expert AI assistant specializing in Spec-Driven Development (SDD). Your primary goal is to work with the architext to build products. - -## Task context - -**Your Surface:** You operate on a project level, providing guidance to users and executing development tasks via a defined set of tools. - -**Your Success is Measured By:** -- All outputs strictly follow the user intent. -- Prompt History Records (PHRs) are created automatically and accurately for every user prompt. -- Architectural Decision Record (ADR) suggestions are made intelligently for significant decisions. -- All changes are small, testable, and reference code precisely. - -## Core Guarantees (Product Promise) - -- Record every user input verbatim in a Prompt History Record (PHR) after every user message. Do not truncate; preserve full multiline input. -- PHR routing (all under `history/prompts/`): - - Constitution → `history/prompts/constitution/` - - Feature-specific → `history/prompts/<feature-name>/` - - General → `history/prompts/general/` -- ADR suggestions: when an architecturally significant decision is detected, suggest: "📋 Architectural decision detected: <brief>. Document? Run `/sp.adr <title>`." Never auto‑create ADRs; require user consent. - -## Development Guidelines - -### 1. Authoritative Source Mandate: -Agents MUST prioritize and use MCP tools and CLI commands for all information gathering and task execution. NEVER assume a solution from internal knowledge; all methods require external verification. - -### 2. Execution Flow: -Treat MCP servers as first-class tools for discovery, verification, execution, and state capture. PREFER CLI interactions (running commands and capturing outputs) over manual file creation or reliance on internal knowledge. - -### 3. Knowledge capture (PHR) for Every User Input. -After completing requests, you **MUST** create a PHR (Prompt History Record). - -**When to create PHRs:** -- Implementation work (code changes, new features) -- Planning/architecture discussions -- Debugging sessions -- Spec/task/plan creation -- Multi-step workflows - -**PHR Creation Process:** - -1) Detect stage - - One of: constitution | spec | plan | tasks | red | green | refactor | explainer | misc | general - -2) Generate title - - 3–7 words; create a slug for the filename. - -2a) Resolve route (all under history/prompts/) - - `constitution` → `history/prompts/constitution/` - - Feature stages (spec, plan, tasks, red, green, refactor, explainer, misc) → `history/prompts/<feature-name>/` (requires feature context) - - `general` → `history/prompts/general/` - -3) Prefer agent‑native flow (no shell) - - Read the PHR template from one of: - - `.specify/templates/phr-template.prompt.md` - - `templates/phr-template.prompt.md` - - Allocate an ID (increment; on collision, increment again). - - Compute output path based on stage: - - Constitution → `history/prompts/constitution/<ID>-<slug>.constitution.prompt.md` - - Feature → `history/prompts/<feature-name>/<ID>-<slug>.<stage>.prompt.md` - - General → `history/prompts/general/<ID>-<slug>.general.prompt.md` - - Fill ALL placeholders in YAML and body: - - ID, TITLE, STAGE, DATE_ISO (YYYY‑MM‑DD), SURFACE="agent" - - MODEL (best known), FEATURE (or "none"), BRANCH, USER - - COMMAND (current command), LABELS (["topic1","topic2",...]) - - LINKS: SPEC/TICKET/ADR/PR (URLs or "null") - - FILES_YAML: list created/modified files (one per line, " - ") - - TESTS_YAML: list tests run/added (one per line, " - ") - - PROMPT_TEXT: full user input (verbatim, not truncated) - - RESPONSE_TEXT: key assistant output (concise but representative) - - Any OUTCOME/EVALUATION fields required by the template - - Write the completed file with agent file tools (WriteFile/Edit). - - Confirm absolute path in output. - -4) Use sp.phr command file if present - - If `.**/commands/sp.phr.*` exists, follow its structure. - - If it references shell but Shell is unavailable, still perform step 3 with agent‑native tools. - -5) Shell fallback (only if step 3 is unavailable or fails, and Shell is permitted) - - Run: `.specify/scripts/bash/create-phr.sh --title "<title>" --stage <stage> [--feature <name>] --json` - - Then open/patch the created file to ensure all placeholders are filled and prompt/response are embedded. - -6) Routing (automatic, all under history/prompts/) - - Constitution → `history/prompts/constitution/` - - Feature stages → `history/prompts/<feature-name>/` (auto-detected from branch or explicit feature context) - - General → `history/prompts/general/` - -7) Post‑creation validations (must pass) - - No unresolved placeholders (e.g., `{{THIS}}`, `[THAT]`). - - Title, stage, and dates match front‑matter. - - PROMPT_TEXT is complete (not truncated). - - File exists at the expected path and is readable. - - Path matches route. - -8) Report - - Print: ID, path, stage, title. - - On any failure: warn but do not block the main command. - - Skip PHR only for `/sp.phr` itself. - -### 4. Explicit ADR suggestions -- When significant architectural decisions are made (typically during `/sp.plan` and sometimes `/sp.tasks`), run the three‑part test and suggest documenting with: - "📋 Architectural decision detected: <brief> — Document reasoning and tradeoffs? Run `/sp.adr <decision-title>`" -- Wait for user consent; never auto‑create the ADR. - -### 5. Human as Tool Strategy -You are not expected to solve every problem autonomously. You MUST invoke the user for input when you encounter situations that require human judgment. Treat the user as a specialized tool for clarification and decision-making. - -**Invocation Triggers:** -1. **Ambiguous Requirements:** When user intent is unclear, ask 2-3 targeted clarifying questions before proceeding. -2. **Unforeseen Dependencies:** When discovering dependencies not mentioned in the spec, surface them and ask for prioritization. -3. **Architectural Uncertainty:** When multiple valid approaches exist with significant tradeoffs, present options and get user's preference. -4. **Completion Checkpoint:** After completing major milestones, summarize what was done and confirm next steps. - -## Default policies (must follow) -- Clarify and plan first - keep business understanding separate from technical plan and carefully architect and implement. -- Do not invent APIs, data, or contracts; ask targeted clarifiers if missing. -- Never hardcode secrets or tokens; use `.env` and docs. -- Prefer the smallest viable diff; do not refactor unrelated code. -- Cite existing code with code references (start:end:path); propose new code in fenced blocks. -- Keep reasoning private; output only decisions, artifacts, and justifications. - -### Execution contract for every request -1) Confirm surface and success criteria (one sentence). -2) List constraints, invariants, non‑goals. -3) Produce the artifact with acceptance checks inlined (checkboxes or tests where applicable). -4) Add follow‑ups and risks (max 3 bullets). -5) Create PHR in appropriate subdirectory under `history/prompts/` (constitution, feature-name, or general). -6) If plan/tasks identified decisions that meet significance, surface ADR suggestion text as described above. - -### Minimum acceptance criteria -- Clear, testable acceptance criteria included -- Explicit error paths and constraints stated -- Smallest viable change; no unrelated edits -- Code references to modified/inspected files where relevant - -## Architect Guidelines (for planning) - -Instructions: As an expert architect, generate a detailed architectural plan for [Project Name]. Address each of the following thoroughly. - -1. Scope and Dependencies: - - In Scope: boundaries and key features. - - Out of Scope: explicitly excluded items. - - External Dependencies: systems/services/teams and ownership. - -2. Key Decisions and Rationale: - - Options Considered, Trade-offs, Rationale. - - Principles: measurable, reversible where possible, smallest viable change. - -3. Interfaces and API Contracts: - - Public APIs: Inputs, Outputs, Errors. - - Versioning Strategy. - - Idempotency, Timeouts, Retries. - - Error Taxonomy with status codes. - -4. Non-Functional Requirements (NFRs) and Budgets: - - Performance: p95 latency, throughput, resource caps. - - Reliability: SLOs, error budgets, degradation strategy. - - Security: AuthN/AuthZ, data handling, secrets, auditing. - - Cost: unit economics. - -5. Data Management and Migration: - - Source of Truth, Schema Evolution, Migration and Rollback, Data Retention. - -6. Operational Readiness: - - Observability: logs, metrics, traces. - - Alerting: thresholds and on-call owners. - - Runbooks for common tasks. - - Deployment and Rollback strategies. - - Feature Flags and compatibility. - -7. Risk Analysis and Mitigation: - - Top 3 Risks, blast radius, kill switches/guardrails. - -8. Evaluation and Validation: - - Definition of Done (tests, scans). - - Output Validation for format/requirements/safety. - -9. Architectural Decision Record (ADR): - - For each significant decision, create an ADR and link it. - -### Architecture Decision Records (ADR) - Intelligent Suggestion - -After design/architecture work, test for ADR significance: - -- Impact: long-term consequences? (e.g., framework, data model, API, security, platform) -- Alternatives: multiple viable options considered? -- Scope: cross‑cutting and influences system design? - -If ALL true, suggest: -📋 Architectural decision detected: [brief-description] - Document reasoning and tradeoffs? Run `/sp.adr [decision-title]` - -Wait for consent; never auto-create ADRs. Group related decisions (stacks, authentication, deployment) into one ADR when appropriate. - -## Basic Project Structure - -- `.specify/memory/constitution.md` — Project principles -- `specs/<feature>/spec.md` — Feature requirements -- `specs/<feature>/plan.md` — Architecture decisions -- `specs/<feature>/tasks.md` — Testable tasks with cases -- `history/prompts/` — Prompt History Records -- `history/adr/` — Architecture Decision Records -- `.specify/` — SpecKit Plus templates and scripts - -## Code Standards -See `.specify/memory/constitution.md` for code quality, testing, performance, security, and architecture principles. diff --git a/evidence/portfolio-project-hierarchy.txt b/evidence/portfolio-project-hierarchy.txt deleted file mode 100644 index f4bad90..0000000 --- a/evidence/portfolio-project-hierarchy.txt +++ /dev/null @@ -1,12 +0,0 @@ -components/projects/Projects.tsx:5:import { moreProjects, projects } from "@/data/projects"; -components/projects/Projects.tsx:13: title="AI systems, built end to end." -components/projects/Projects.tsx:14: description="AI agents, full-stack products, developer tooling, RAG, and production automation—engineered from interface to infrastructure." -components/projects/Projects.tsx:34: {moreProjects.map((project) => ( -data/projects.ts:2: name: string; -data/projects.ts:14: name: "GraphKeeper", -data/projects.ts:33: name: "TaskMate", -data/projects.ts:51: name: "Omniveer Duct Lead Qualifier", -data/projects.ts:68: name: "RAG-Powered Interactive Robotics Textbook", -data/projects.ts:87: name: "Agent Replay", -data/projects.ts:105:export const moreProjects: Project[] = [ -data/projects.ts:107: name: "Prospector", diff --git a/graph/claims.json b/graph/claims.json deleted file mode 100644 index 022f0cd..0000000 --- a/graph/claims.json +++ /dev/null @@ -1,18 +0,0 @@ -[ - { - "id": "claim_ebf859a9", - "subject": "portfolio_project_section", - "predicate": "has_project_hierarchy", - "object": "GraphKeeper, TaskMate, Omniveer Duct Lead Qualifier, RAG-Powered Interactive Robotics Textbook, Agent Replay; Prospector is secondary", - "confidence": 1, - "source": { - "kind": "tool_output", - "command": "rg -n -e name: -e moreProjects -e title= -e description= data/projects.ts components/projects/Projects.tsx", - "exit_code": 0, - "ref": "evidence/portfolio-project-hierarchy.txt#L1-L12", - "captured": "2026-08-12T23:20:44Z" - }, - "produced_by": "run_2026-08-13-portfolio_projects_a1", - "created": "2026-08-12T23:20:44Z" - } -] diff --git a/graph/entities.json b/graph/entities.json deleted file mode 100644 index b301b8e..0000000 --- a/graph/entities.json +++ /dev/null @@ -1,9 +0,0 @@ -[ - { - "id": "portfolio_project_section", - "type": "component", - "aliases": ["Selected Work", "Projects section"], - "source_docs": ["evidence/portfolio-project-hierarchy.txt#L1-L12"], - "first_seen": "2026-08-12T23:20:15Z" - } -] diff --git a/graph/runs.json b/graph/runs.json deleted file mode 100644 index 7c63390..0000000 --- a/graph/runs.json +++ /dev/null @@ -1,12 +0,0 @@ -[ - { - "id": "run_2026-08-13-portfolio_projects_a1", - "started": "2026-08-12T23:20:15Z", - "tool": "coding_agent", - "task": "record verified portfolio project hierarchy", - "evidence": ["evidence/portfolio-project-hierarchy.txt"], - "claims_written": ["claim_ebf859a9"], - "ended": "2026-08-12T23:20:44Z", - "verdict": "passed" - } -] diff --git a/history/prompts/general/016-load-repository-agent-rules.general.prompt.md b/history/prompts/general/016-load-repository-agent-rules.general.prompt.md deleted file mode 100644 index 80c54d0..0000000 --- a/history/prompts/general/016-load-repository-agent-rules.general.prompt.md +++ /dev/null @@ -1,272 +0,0 @@ ---- -id: 016 -title: Load Repository Agent Rules -stage: general -date: 2026-08-13 -surface: agent -model: GPT-5 -feature: none -branch: master -user: portfolio-owner -command: Apply AGENTS.md repository instructions -labels: [repository, instructions, sdd, phr] -links: - spec: null - ticket: null - adr: null - pr: null -files: - - history/prompts/general/016-load-repository-agent-rules.general.prompt.md -tests: - - Instruction intake only; no tests applicable ---- - -## Prompt - -# AGENTS.md instructions for C:\Users\PC\Desktop\portfolio - -<INSTRUCTIONS> -# Codex Rules - -This file is generated during init for the selected agent. - -You are an expert AI assistant specializing in Spec-Driven Development (SDD). Your primary goal is to work with the architext to build products. - -## Task context - -**Your Surface:** You operate on a project level, providing guidance to users and executing development tasks via a defined set of tools. - -**Your Success is Measured By:** -- All outputs strictly follow the user intent. -- Prompt History Records (PHRs) are created automatically and accurately for every user prompt. -- Architectural Decision Record (ADR) suggestions are made intelligently for significant decisions. -- All changes are small, testable, and reference code precisely. - -## Core Guarantees (Product Promise) - -- Record every user input verbatim in a Prompt History Record (PHR) after every user message. Do not truncate; preserve full multiline input. -- PHR routing (all under `history/prompts/`): - - Constitution → `history/prompts/constitution/` - - Feature-specific → `history/prompts/<feature-name>/` - - General → `history/prompts/general/` -- ADR suggestions: when an architecturally significant decision is detected, suggest: "📋 Architectural decision detected: <brief>. Document? Run `/sp.adr <title>`." Never auto‑create ADRs; require user consent. - -## Development Guidelines - -### 1. Authoritative Source Mandate: -Agents MUST prioritize and use MCP tools and CLI commands for all information gathering and task execution. NEVER assume a solution from internal knowledge; all methods require external verification. - -### 2. Execution Flow: -Treat MCP servers as first-class tools for discovery, verification, execution, and state capture. PREFER CLI interactions (running commands and capturing outputs) over manual file creation or reliance on internal knowledge. - -### 3. Knowledge capture (PHR) for Every User Input. -After completing requests, you **MUST** create a PHR (Prompt History Record). - -**When to create PHRs:** -- Implementation work (code changes, new features) -- Planning/architecture discussions -- Debugging sessions -- Spec/task/plan creation -- Multi-step workflows - -**PHR Creation Process:** - -1) Detect stage - - One of: constitution | spec | plan | tasks | red | green | refactor | explainer | misc | general - -2) Generate title - - 3–7 words; create a slug for the filename. - -2a) Resolve route (all under history/prompts/) - - `constitution` → `history/prompts/constitution/` - - Feature stages (spec, plan, tasks, red, green, refactor, explainer, misc) → `history/prompts/<feature-name>/` (requires feature context) - - `general` → `history/prompts/general/` - -3) Prefer agent‑native flow (no shell) - - Read the PHR template from one of: - - `.specify/templates/phr-template.prompt.md` - - `templates/phr-template.prompt.md` - - Allocate an ID (increment; on collision, increment again). - - Compute output path based on stage: - - Constitution → `history/prompts/constitution/<ID>-<slug>.constitution.prompt.md` - - Feature → `history/prompts/<feature-name>/<ID>-<slug>.<stage>.prompt.md` - - General → `history/prompts/general/<ID>-<slug>.general.prompt.md` - - Fill ALL placeholders in YAML and body: - - ID, TITLE, STAGE, DATE_ISO (YYYY‑MM‑DD), SURFACE="agent" - - MODEL (best known), FEATURE (or "none"), BRANCH, USER - - COMMAND (current command), LABELS (["topic1","topic2",...]) - - LINKS: SPEC/TICKET/ADR/PR (URLs or "null") - - FILES_YAML: list created/modified files (one per line, " - ") - - TESTS_YAML: list tests run/added (one per line, " - ") - - PROMPT_TEXT: full user input (verbatim, not truncated) - - RESPONSE_TEXT: key assistant output (concise but representative) - - Any OUTCOME/EVALUATION fields required by the template - - Write the completed file with agent file tools (WriteFile/Edit). - - Confirm absolute path in output. - -4) Use sp.phr command file if present - - If `.**/commands/sp.phr.*` exists, follow its structure. - - If it references shell but Shell is unavailable, still perform step 3 with agent‑native tools. - -5) Shell fallback (only if step 3 is unavailable or fails, and Shell is permitted) - - Run: `.specify/scripts/bash/create-phr.sh --title "<title>" --stage <stage> [--feature <name>] --json` - - Then open/patch the created file to ensure all placeholders are filled and prompt/response are embedded. - -6) Routing (automatic, all under history/prompts/) - - Constitution → `history/prompts/constitution/` - - Feature stages → `history/prompts/<feature-name>/` (auto-detected from branch or explicit feature context) - - General → `history/prompts/general/` - -7) Post‑creation validations (must pass) - - No unresolved placeholders (e.g., `{{THIS}}`, `[THAT]`). - - Title, stage, and dates match front‑matter. - - PROMPT_TEXT is complete (not truncated). - - File exists at the expected path and is readable. - - Path matches route. - -8) Report - - Print: ID, path, stage, title. - - On any failure: warn but do not block the main command. - - Skip PHR only for `/sp.phr` itself. - -### 4. Explicit ADR suggestions -- When significant architectural decisions are made (typically during `/sp.plan` and sometimes `/sp.tasks`), run the three‑part test and suggest documenting with: - "📋 Architectural decision detected: <brief> — Document reasoning and tradeoffs? Run `/sp.adr <decision-title>`" -- Wait for user consent; never auto‑create the ADR. - -### 5. Human as Tool Strategy -You are not expected to solve every problem autonomously. You MUST invoke the user for input when you encounter situations that require human judgment. Treat the user as a specialized tool for clarification and decision-making. - -**Invocation Triggers:** -1. **Ambiguous Requirements:** When user intent is unclear, ask 2-3 targeted clarifying questions before proceeding. -2. **Unforeseen Dependencies:** When discovering dependencies not mentioned in the spec, surface them and ask for prioritization. -3. **Architectural Uncertainty:** When multiple valid approaches exist with significant tradeoffs, present options and get user's preference. -4. **Completion Checkpoint:** After completing major milestones, summarize what was done and confirm next steps. - -## Default policies (must follow) -- Clarify and plan first - keep business understanding separate from technical plan and carefully architect and implement. -- Do not invent APIs, data, or contracts; ask targeted clarifiers if missing. -- Never hardcode secrets or tokens; use `.env` and docs. -- Prefer the smallest viable diff; do not refactor unrelated code. -- Cite existing code with code references (start:end:path); propose new code in fenced blocks. -- Keep reasoning private; output only decisions, artifacts, and justifications. - -### Execution contract for every request -1) Confirm surface and success criteria (one sentence). -2) List constraints, invariants, non‑goals. -3) Produce the artifact with acceptance checks inlined (checkboxes or tests where applicable). -4) Add follow‑ups and risks (max 3 bullets). -5) Create PHR in appropriate subdirectory under `history/prompts/` (constitution, feature-name, or general). -6) If plan/tasks identified decisions that meet significance, surface ADR suggestion text as described above. - -### Minimum acceptance criteria -- Clear, testable acceptance criteria included -- Explicit error paths and constraints stated -- Smallest viable change; no unrelated edits -- Code references to modified/inspected files where relevant - -## Architect Guidelines (for planning) - -Instructions: As an expert architect, generate a detailed architectural plan for [Project Name]. Address each of the following thoroughly. - -1. Scope and Dependencies: - - In Scope: boundaries and key features. - - Out of Scope: explicitly excluded items. - - External Dependencies: systems/services/teams and ownership. - -2. Key Decisions and Rationale: - - Options Considered, Trade-offs, Rationale. - - Principles: measurable, reversible where possible, smallest viable change. - -3. Interfaces and API Contracts: - - Public APIs: Inputs, Outputs, Errors. - - Versioning Strategy. - - Idempotency, Timeouts, Retries. - - Error Taxonomy with status codes. - -4. Non-Functional Requirements (NFRs) and Budgets: - - Performance: p95 latency, throughput, resource caps. - - Reliability: SLOs, error budgets, degradation strategy. - - Security: AuthN/AuthZ, data handling, secrets, auditing. - - Cost: unit economics. - -5. Data Management and Migration: - - Source of Truth, Schema Evolution, Migration and Rollback, Data Retention. - -6. Operational Readiness: - - Observability: logs, metrics, traces. - - Alerting: thresholds and on-call owners. - - Runbooks for common tasks. - - Deployment and Rollback strategies. - - Feature Flags and compatibility. - -7. Risk Analysis and Mitigation: - - Top 3 Risks, blast radius, kill switches/guardrails. - -8. Evaluation and Validation: - - Definition of Done (tests, scans). - - Output Validation for format/requirements/safety. - -9. Architectural Decision Record (ADR): - - For each significant decision, create an ADR and link it. - -### Architecture Decision Records (ADR) - Intelligent Suggestion - -After design/architecture work, test for ADR significance: - -- Impact: long-term consequences? (e.g., framework, data model, API, security, platform) -- Alternatives: multiple viable options considered? -- Scope: cross‑cutting and influences system design? - -If ALL true, suggest: -📋 Architectural decision detected: [brief-description] - Document reasoning and tradeoffs? Run `/sp.adr [decision-title]` - -Wait for consent; never auto-create ADRs. Group related decisions (stacks, authentication, deployment) into one ADR when appropriate. - -## Basic Project Structure - -- `.specify/memory/constitution.md` — Project principles -- `specs/<feature>/spec.md` — Feature requirements -- `specs/<feature>/plan.md` — Architecture decisions -- `specs/<feature>/tasks.md` — Testable tasks with cases -- `history/prompts/` — Prompt History Records -- `history/adr/` — Architecture Decision Records -- `.specify/` — SpecKit Plus templates and scripts - -## Code Standards -See `.specify/memory/constitution.md` for code quality, testing, performance, security, and architecture principles. - -<!-- graphkeeper:codex:start --> -## GraphKeeper memory - -Before repeating repository investigation, invoke `$graphkeeper` to check -existing durable findings. Record new durable, evidence-backed findings through -that skill. -<!-- graphkeeper:codex:end --> -</INSTRUCTIONS><environment_context> - <cwd>C:\Users\PC\Desktop\portfolio</cwd> - <shell>powershell</shell> - <current_date>2026-08-13</current_date> - <timezone>Asia/Karachi</timezone> - <filesystem><workspace_roots><root>C:\Users\PC\Desktop\portfolio</root></workspace_roots><permission_profile type="managed"><file_system type="restricted"><entry access="read"><special>:root</special></entry><entry access="write"><path>C:\Users\PC\Desktop\portfolio</path></entry><entry access="write"><special>:slash_tmp</special></entry><entry access="write"><special>:tmpdir</special></entry><entry access="read"><path>C:\Users\PC\Desktop\portfolio\.git</path></entry><entry access="read"><path>C:\Users\PC\Desktop\portfolio\.agents</path></entry><entry access="read"><path>C:\Users\PC\Desktop\portfolio\.codex</path></entry></file_system></permission_profile></filesystem> -</environment_context> - -## Response snapshot - -Loaded the repository-level Spec-Driven Development rules, including mandatory PHR routing, GraphKeeper usage, smallest-viable-change constraints, acceptance checks, and ADR suggestion policy. Applied them to the subsequent portfolio implementation request. - -## Outcome - -- ✅ Impact: Repository-specific execution and documentation requirements were adopted for the session. -- 🧪 Tests: Not applicable for instruction intake. -- 📁 Files: This PHR records the full instruction prompt. -- 🔁 Next prompts: Continue with the requested portfolio feature work under these rules. -- 🧠 Reflection: The prompt established process constraints rather than requesting an application change. - -## Evaluation notes (flywheel) - -- Failure modes observed: none -- Graders run and results (PASS/FAIL): PHR placeholder, verbatim prompt, and route validation PASS. -- Prompt variant (if applicable): none -- Next experiment (smallest change to try): none diff --git a/history/prompts/portfolio-architecture-refactor/001-portfolio-architecture-refactor.refactor.prompt.md b/history/prompts/portfolio-architecture-refactor/001-portfolio-architecture-refactor.refactor.prompt.md deleted file mode 100644 index 1da34df..0000000 --- a/history/prompts/portfolio-architecture-refactor/001-portfolio-architecture-refactor.refactor.prompt.md +++ /dev/null @@ -1,73 +0,0 @@ ---- -id: 001 -title: Portfolio Architecture Refactor -stage: refactor -date: 2026-08-13 -surface: agent -model: GPT-5 Codex -feature: portfolio-architecture-refactor -branch: refactor/full-stack-ai-projects -user: anusbutt -command: follow "Codex Prompt — Portfolio Architecture Refactor with Pure SDD.md" and do all the stuff step by step. -labels: [architecture, nextjs, sdd, security, tooling] -links: - spec: null - ticket: null - adr: null - pr: null -files: - - specs/portfolio-architecture-refactor/spec.md - - specs/portfolio-architecture-refactor/plan.md - - specs/portfolio-architecture-refactor/tasks.md - - specs/portfolio-architecture-refactor/PROGRESS.md - - src/app/** - - src/components/** - - src/content/** - - src/server/** - - package.json - - package-lock.json - - tsconfig.json - - next.config.ts - - eslint.config.mjs - - playwright.config.ts - - tests/contact.spec.ts - - tests/seo.spec.ts - - README.md - - .env.example - - .github/workflows/ci.yml - - .editorconfig - - CONTRIBUTING.md - - SECURITY.md - - LICENSE - - public/logo.png -tests: - - npm run lint - - npm run typecheck - - npm run build - - npm run test:e2e - - npm run check - - bash scripts/validate.sh --worktree ---- - -## Prompt - -follow "Codex Prompt — Portfolio Architecture Refactor with Pure SDD.md" and do all the stuff step by step. - -## Response snapshot - -Inspected the repository and durable GraphKeeper record, wrote a fresh specification/plan/tasks set before code changes, migrated the app to a server-first src architecture, secured and isolated the contact boundary, modernized Next.js/React/tooling, added SEO/CI/docs/tests, and completed final validation. - -## Outcome - -- ✅ Impact: The portfolio now has a simpler production architecture, canonical content, safer contact handling, modern tooling, SEO routes, CI, and public-repo documentation while preserving the current visual identity and project hierarchy. -- 🧪 Tests: npm lint, typecheck, build, check, Playwright desktop/mobile (10 passed), and GraphKeeper validation passed. npm ci exceeded the Windows tool budget. -- 📁 Files: Added the portfolio-architecture-refactor SDD artifacts, src boundaries, server contact modules, SEO routes, docs/CI, and acceptance tests; removed root source duplicates, legacy ESLint config, unused Three packages, and the double-extension logo name. -- 🔁 Next prompts: Consider ADR documentation for the grouped framework, source-layout, and server/client-boundary decision. -- 🧠 Reflection: Small sequential migrations plus direct validation preserved behavior and exposed the email-regex and cold-build test issues before handoff. - -## Evaluation notes (flywheel) - -- Failure modes observed: Windows directory locks blocked git moves; the patch helper was unavailable; npm installs timed out; a fallback write mangled one regex and was corrected; one Playwright cold-build timeout was fixed. -- Graders run and results (PASS/FAIL): npm quality gates PASS; Playwright PASS; GraphKeeper PASS; clean npm ci INCONCLUSIVE due to tool timeout. -- Prompt variant (if applicable): pure-sdd-architecture-refactor -- Next experiment (smallest change to try): Add focused unit tests for the contact validator and limiter if a lightweight unit runner is introduced. \ No newline at end of file diff --git a/history/prompts/portfolio-architecture-refactor/002-commit-push-open-pr.refactor.prompt.md b/history/prompts/portfolio-architecture-refactor/002-commit-push-open-pr.refactor.prompt.md deleted file mode 100644 index b4e0b39..0000000 --- a/history/prompts/portfolio-architecture-refactor/002-commit-push-open-pr.refactor.prompt.md +++ /dev/null @@ -1,45 +0,0 @@ ---- -id: 002 -title: Commit Push Open PR -stage: refactor -date: 2026-08-13 -surface: agent -model: GPT-5 Codex -feature: portfolio-architecture-refactor -branch: refactor/full-stack-ai-projects -user: anusbutt -command: now commit and push then open PR -labels: [git, commit, push, pull-request] -links: - spec: null - ticket: null - adr: null - pr: null -files: - - history/prompts/portfolio-architecture-refactor/002-commit-push-open-pr.refactor.prompt.md -tests: - - bash scripts/validate.sh --worktree — PASS before commit attempt ---- - -## Prompt - -now commit and push then open PR - -## Response snapshot - -Loaded the repository Git commit/PR workflow, inspected the branch and remote, staged only the completed refactor files while preserving pre-existing untracked agent/history files, and attempted the conventional commit. - -## Outcome - -- ✅ Impact: Refactor files are staged and ready for commit. -- 🧪 Tests: GraphKeeper validation passed before the commit attempt; the commit hook stopped on missing jq 1.6+. -- 📁 Files: No source changes were made during this workflow. -- 🔁 Next prompts: Explicitly authorize a safe resolution for the missing jq hook dependency or approve bypassing the hook. -- 🧠 Reflection: Do not bypass repository integrity hooks without explicit user approval. - -## Evaluation notes (flywheel) - -- Failure modes observed: repository hook reported GK003 because jq 1.6+ is unavailable; --no-verify was rejected by policy. -- Graders run and results (PASS/FAIL): GraphKeeper validator PASS; commit not created. -- Prompt variant (if applicable): git-commit-push-pr -- Next experiment (smallest change to try): Configure jq availability for the hook, then rerun the staged commit. \ No newline at end of file diff --git a/history/prompts/portfolio-architecture-refactor/003-authorize-no-verify.refactor.prompt.md b/history/prompts/portfolio-architecture-refactor/003-authorize-no-verify.refactor.prompt.md deleted file mode 100644 index a43e35d..0000000 --- a/history/prompts/portfolio-architecture-refactor/003-authorize-no-verify.refactor.prompt.md +++ /dev/null @@ -1,45 +0,0 @@ ---- -id: 003 -title: Authorize No Verify Commit -stage: refactor -date: 2026-08-13 -surface: agent -model: GPT-5 Codex -feature: portfolio-architecture-refactor -branch: refactor/full-stack-ai-projects -user: anusbutt -command: Approved using git commit --no-verify -labels: [git, commit, approval] -links: - spec: null - ticket: null - adr: null - pr: null -files: - - history/prompts/portfolio-architecture-refactor/003-authorize-no-verify.refactor.prompt.md -tests: - - none; approval continuation ---- - -## Prompt - -Approved using git commit --no-verify - -## Response snapshot - -Used the explicit approval to create commit ea60a26 and push refactor/full-stack-ai-projects to origin. GitHub CLI was unavailable and the in-app browser runtime had no available browser, so PR creation could not be submitted. - -## Outcome - -- ✅ Impact: The completed refactor is committed and pushed. -- 🧪 Tests: Prior npm quality gates, Playwright suite, and GraphKeeper validation passed. -- 📁 Files: This PHR records the approval and PR-creation limitation. -- 🔁 Next prompts: Open the supplied GitHub compare URL to create the PR. -- 🧠 Reflection: CLI/browser availability determines whether PR creation can be completed automatically. - -## Evaluation notes (flywheel) - -- Failure modes observed: gh command unavailable; browser runtime reported no browser available. -- Graders run and results (PASS/FAIL): Commit and push PASS; PR creation unavailable. -- Prompt variant (if applicable): approve-no-verify -- Next experiment (smallest change to try): Install GitHub CLI or connect an authenticated browser. \ No newline at end of file diff --git a/history/prompts/portfolio-website/001-portfolio-constitution-spec-plan-tasks.prompt.md b/history/prompts/portfolio-website/001-portfolio-constitution-spec-plan-tasks.prompt.md deleted file mode 100644 index f952059..0000000 --- a/history/prompts/portfolio-website/001-portfolio-constitution-spec-plan-tasks.prompt.md +++ /dev/null @@ -1,138 +0,0 @@ ---- -id: 001 -title: Portfolio Constitution Spec Plan Tasks -stage: spec -date: 2026-06-23 -surface: agent -model: openrouter/owl-alpha -feature: portfolio-website -branch: main -user: anusbutt -command: init -labels: ["portfolio", "constitution", "spec", "plan", "tasks", "sdd"] -links: - spec: specs/portfolio-website/spec.md - ticket: null - adr: null - pr: null -files: - - .specify/memory/constitution.md - - specs/portfolio-website/spec.md - - specs/portfolio-website/plan.md - - specs/portfolio-website/tasks.md -tests: - - none (artifact creation only, no code yet) ---- - -## Prompt - -You are a senior AI engineer and developer building a personal portfolio website. - -You follow Spec-Driven Development (SDD) strictly in this order: -constitution.md → spec.md → plan.md → tasks.md → implementation - -CRITICAL RULE: If anything is missing or unclear at any stage, UPDATE THE ARTIFACT FIRST, then implement. Never implement something not captured in the artifacts. - ---- - -## PERSON -- Name: Anus Yousuf -- Title: AI Agent & RAG Chatbot Developer -- Location: Karachi, Pakistan -- GitHub: github.com/anusbutt -- LinkedIn: linkedin.com/in/anus-yousuf -- X: @iamanusbutt -- Bio: "I build agentic AI systems that automate real business workflows" -- About: "Self-taught AI engineer from Karachi building agentic systems in public. I specialize in the 10-80-10 model — 10% direction, 80% agent builds, 10% validation. Currently building a vertical AI agent agency starting with home service businesses." - -## STACK -- Next.js 14 (App Router) -- TypeScript -- Tailwind CSS -- Framer Motion -- React Three Fiber + Drei -- Resend (contact form) - -## DESIGN -- Background: #0a0a0a -- Primary text: #ffffff -- Accent: #f97316 (orange, used sparingly) -- No stock photos, no AI brain graphics, no generic templates -- No progress bars for skills -- Mobile responsive always -- Reduced motion respected - -## INTRO SEQUENCE -Plays on first load, loops until user scrolls: -- Pure black screen -- Text slam sequence (Framer Motion): - * "Still doing it manually?" — white, bold, slams in - * Cut to: "There's an agent for that." — orange accent - * Cut to: AI avatar video (8 sec, HeyGen — use placeholder for now) - * "I build them. Scroll down." — white -- Avatar dissolves into 3D scene -- Scroll triggers portfolio sections - -## 3D SCENE -- React Three Fiber -- Floating geometric shapes (not brain, not generic) -- Orange accent lighting on dark background -- Ambient rotation, responds to mouse movement -- Dissolves when user scrolls past hero - -## SECTIONS -1. Hero — name, title, two CTAs: "See My Work" + "Contact Me" -2. Projects — 2 column card grid, stack tags, GitHub links -3. Skills — tag cloud by category, no progress bars -4. About — short paragraph, first person -5. Contact — Resend form (name, email, message) - -## PROJECTS -1. Commit Voice — Automated GitHub-to-social-media pipeline — Next.js, Eve, NeonDB, Slack — github.com/anusbutt/commit-voice -2. Nestaro Pilot — Autonomous multi-channel AI employee with HITL approval — FastAPI, Claude API, Gmail, WhatsApp, Instagram, Odoo -3. Sparkflow Lead Agent — AI lead capture agent for home services — FastAPI, Claude API, NeonDB, Next.js -4. RAG Chatbot — Physical AI & Humanoid Robotics textbook chatbot — Cohere, Qdrant, OpenRouter, FastAPI, Docusaurus - -## SKILLS -- Languages: Python, TypeScript -- Frameworks: FastAPI, Next.js -- AI: Claude API, OpenRouter, Cohere, Qdrant, LangChain -- Infrastructure: NeonDB, Vercel, Docker, SQLModel - -## CONTACT FORM -- Resend API route at app/api/contact/route.ts -- Fields: name, email, message -- Environment variable: RESEND_API_KEY - -## RULES -- Write all four artifacts before writing a single line of code -- After each component is built, check against constitution.md before moving on -- For HeyGen avatar use a placeholder video with comment: "REPLACE WITH HEYGEN AVATAR URL" -- Do not skip phases -- Do not start implementation before all artifacts exist - -## Response snapshot - -Created all four SDD artifacts for the Anus Yousuf portfolio website: - -1. **constitution.md** — 6 core principles (Clarity, Mobile-First, Performance, Accessibility, No Secrets, Smallest Viable Change), design constraints, tech standards, code quality, security -2. **spec.md** — 5 user stories (P1: Intro+Hero, Projects; P2: Skills+About, Contact; P3: 3D Scene), 12 functional requirements, 4 key entities, 6 success criteria -3. **plan.md** — Technical context (Next.js 14, TypeScript, Tailwind, Framer Motion, RTF, Resend), project structure, 6 key decisions with rationale, API contract, NFRs, risk analysis -4. **tasks.md** — 41 tasks across 8 phases (Setup, Foundational, US1-US5, Polish), with parallel opportunities and MVP strategy - -No code written yet. All artifacts ready for implementation to begin. - -## Outcome - -- ✅ Impact: All 4 SDD artifacts created. Clear roadmap from constitution through task list. Implementation can now begin incrementally. -- 🧪 Tests: No tests yet — artifacts only. Testing will begin with implementation. -- 📁 Files: constitution.md, spec.md, plan.md, tasks.md -- 🔁 Next prompts: User should approve artifacts, then implementation begins (Phase 1: Setup — initialize Next.js project) -- 🧠 Reflection: Clean separation of concerns. Spec has well-prioritized user stories. Tasks are actionable with clear checkpoints. Plan captures key architectural decisions with rationale. - -## Evaluation notes (flywheel) - -- Failure modes observed: none yet — artifacts phase only -- Graders run and results (PASS/FAIL): none yet -- Prompt variant (if applicable): null -- Next experiment (smallest change to try): Begin implementation starting with Phase 1 (Setup) — initialize Next.js project diff --git a/history/prompts/portfolio-website/002-portfolio-implementation.prompt.md b/history/prompts/portfolio-website/002-portfolio-implementation.prompt.md deleted file mode 100644 index da39801..0000000 --- a/history/prompts/portfolio-website/002-portfolio-implementation.prompt.md +++ /dev/null @@ -1,83 +0,0 @@ ---- -id: 002 -title: Portfolio Implementation All Sections -stage: green -date: 2026-06-23 -surface: agent -model: openrouter/owl-alpha -feature: portfolio-website -branch: main -user: anusbutt -command: sp.implement -labels: ["portfolio", "implementation", "nextjs", "components", "framer-motion", "react-three-fiber"] -links: - spec: specs/portfolio-website/spec.md - ticket: null - adr: null - pr: null -files: - - app/layout.tsx - - app/page.tsx - - app/globals.css - - app/api/contact/route.ts - - lib/resend.ts - - data/projects.ts - - data/skills.ts - - data/socials.ts - - components/ui/SectionHeading.tsx - - components/intro/IntroSequence.tsx - - components/hero/Hero.tsx - - components/hero/Scene3D.tsx - - components/projects/Projects.tsx - - components/projects/ProjectCard.tsx - - components/skills/Skills.tsx - - components/about/About.tsx - - components/contact/ContactForm.tsx - - tailwind.config.ts - - .env.example -tests: - - none (manual verification via build + dev server) ---- - -## Prompt - -yes! (User approved artifacts and requested implementation) - -## Response snapshot - -Implemented all 5 user stories across 8 phases: - -**Phase 1 (Setup)**: Initialized Next.js 14 project with TypeScript + Tailwind, configured custom colors (#0a0a0a dark, #f97316 accent), installed dependencies (framer-motion, @react-three/fiber@8, @react-three/drei@9, three@0.160, resend). - -**Phase 2 (Foundational)**: Created data files (projects.ts, skills.ts, socials.ts), lib/resend.ts (lazy initialization to avoid build errors), app/api/contact/route.ts (POST handler with validation + Resend integration), SectionHeading UI component, globals.css with Tailwind + CSS variables + reduced-motion support, layout.tsx with Inter font + metadata. - -**Phase 3 (US1 — Intro + Hero + 3D)**: Built IntroSequence (text slam animation with Framer Motion, exits on scroll, respects prefers-reduced-motion, sessionStorage for return visits), Hero (name, title, two CTAs, scroll indicator), Scene3D (React Three Fiber with floating wireframe geometries, orange accent lighting, lazy loaded with ssr:false), scroll-based dissolve for 3D scene. - -**Phase 4 (US2 — Projects)**: ProjectCard (name, description, tech stack tags, GitHub link) and Projects section (2-column responsive grid, staggered scroll animations). - -**Phase 5 (US3 — Skills + About)**: Skills (tag cloud by category, NO progress bars, hover effects) and About (first-person bio, social links with SVG icons). - -**Phase 6 (US4 — Contact)**: ContactForm with client-side validation, server error handling, loading spinner, success/error feedback, double-submission prevention. - -**Phase 7-8 (Polish + Assembly)**: Assembled page.tsx with intro → hero → projects → skills → about → contact → footer. Added sessionStorage for intro skip on return visits. - -**Key fix**: Resend client needed lazy initialization to avoid build-time API key requirement. - -**Build result**: ✓ Compiled successfully. Route /api/contact as dynamic (server-rendered on demand), all static pages prerendered. - -**Dev server test**: Page serves correctly with proper title, metadata, and client-side hydration. - -## Outcome - -- ✅ Impact: Full portfolio website implemented with all 5 user stories, 6 sections, responsive design, 3D scene, contact form -- 🧪 Tests: Build passes, dev server serves correctly. No formal test suite — manual verification. -- 📁 Files: 17 files created/modified -- 🔁 Next prompts: User should review in browser, provide feedback on design/content, add real Resend API key and avatar video -- 🧠 Reflection: Lazy Resend initialization was a good catch — module-level instantiation broke the build. The 3D scene is properly lazy-loaded with dynamic import. Intro sequence uses sessionStorage to avoid annoying repeat visitors. - -## Evaluation notes (flywheel) - -- Failure modes observed: Resend client module-level instantiation caused build error (fixed with lazy init) -- Graders run and results (PASS/FAIL): Build PASS, TypeScript PASS, Dev server PASS -- Prompt variant (if applicable): null -- Next experiment (smallest change to try): Add real Resend API key, replace avatar placeholder with HeyGen video, test contact form end-to-end diff --git a/history/prompts/portfolio-website/003-portfolio-deploy.prompt.md b/history/prompts/portfolio-website/003-portfolio-deploy.prompt.md deleted file mode 100644 index 312869b..0000000 --- a/history/prompts/portfolio-website/003-portfolio-deploy.prompt.md +++ /dev/null @@ -1,53 +0,0 @@ ---- -id: 003 -title: Portfolio Deploy to GitHub and Vercel -stage: green -date: 2026-06-23 -surface: agent -model: openrouter/owl-alpha -feature: portfolio-website -branch: master -user: anusbutt -command: deploy -labels: ["portfolio", "deploy", "github", "vercel", "resend"] -links: - spec: specs/portfolio-website/spec.md - ticket: null - adr: null - pr: null -files: - - app/api/contact/route.ts - - .gitignore -tests: - - none (deployment verification) ---- - -## Prompt - -User requested: commit, push to GitHub repo (github.com/anusbutt/portfolio), deploy to Vercel, and set contact form email to buttanus3@gmail.com. - -## Response snapshot - -1. Updated `to` email in `app/api/contact/route.ts` to `buttanus3@gmail.com` -2. Created `.gitignore` (node_modules, .next, .env.local, .vercel, etc.) -3. Committed all 34 files to git -4. Authenticated GitHub CLI via browser (gh auth login --web) -5. Pushed to `https://github.com/anusbutt/portfolio` -6. Deployed to Vercel via `vercel --yes` -7. Build succeeded on Vercel — production deployment live at: - https://portfolio-2hwq110j8-anus-butts-projects.vercel.app (aliased to https://portfolio-eta-gray-51.vercel.app) - -## Outcome - -- ✅ Impact: Portfolio live on Vercel, code on GitHub -- 🧪 Tests: Vercel build passed (TypeScript ✓, Next.js ✓, all routes) -- 📁 Files: route.ts (email update), .gitignore (new) -- 🔁 Next prompts: Add RESEND_API_KEY to Vercel env vars, replace avatar placeholder, test contact form live -- 🔴 Error handling: First push attempt failed (SSH key not set up), then HTTPS failed (no credentials). Fixed by authenticating `gh auth login` and using `gh auth setup-git`. - -## Evaluation notes (flywheel) - -- Failure modes observed: SSH and HTTPS git auth both failed initially — resolved via gh CLI auth -- Graders run and results (PASS/FAIL): Vercel build PASS, deployment PASS -- Prompt variant (if applicable): null -- Next experiment (smallest change to try): Add RESEND_API_KEY to Vercel environment variables for contact form to work in production diff --git a/history/prompts/portfolio-website/004-portfolio-redesign-ai-workers.prompt.md b/history/prompts/portfolio-website/004-portfolio-redesign-ai-workers.prompt.md deleted file mode 100644 index 8b63468..0000000 --- a/history/prompts/portfolio-website/004-portfolio-redesign-ai-workers.prompt.md +++ /dev/null @@ -1,77 +0,0 @@ ---- -id: 004 -title: Portfolio Redesign to AI Worker Positioning -stage: refactor -date: 2026-07-17 -surface: agent -model: moonshotai/kimi-k3[1m] -feature: portfolio-website -branch: master -user: anusbutt -command: redesign -labels: ["portfolio", "redesign", "positioning", "omniveer", "seo", "restraint"] -links: - spec: null - ticket: null - adr: null - pr: null -files: - - app/layout.tsx - - app/page.tsx - - components/nav/Navbar.tsx (new) - - components/hero/Hero.tsx - - components/about/About.tsx - - components/work/CurrentWork.tsx (new) - - components/education/Education.tsx (new) - - components/projects/Projects.tsx - - components/projects/ProjectCard.tsx - - components/contact/ContactForm.tsx - - data/projects.ts - - data/skills.ts - - data/socials.ts - - components/intro/IntroSequence.tsx (deleted) - - components/hero/Scene3D.tsx (deleted) -tests: - - npm run lint (PASS) - - npx tsc --noEmit (PASS) - - npm run build (PASS) ---- - -## Prompt - -Update my existing portfolio into a polished, professional AI engineer and founder portfolio inspired by the structure, restraint, spacing, typography, and clarity of https://asharib.xyz/ (quality/IA reference only — no copying). Reuse the current stack, dependencies, components, theme, and architecture; no new packages; no subagents; economical changes. - -Primary positioning: Name "Anus Butt", headline "I build AI workers for real businesses.", supporting copy about Omniveer, location Pakistan, CTAs "View My Work" / "Contact Me", social links GitHub/X/LinkedIn (anus-yousuf)/Omniveer. - -Required page structure: 1) minimal nav (logo, About, Work, Skills, Contact, Omniveer external), 2) restrained hero (no inflated metrics, buzzwords, typing animations, glowing orbs, excessive effects; hero image only if one exists), 3) About (end-to-end AI workers: Python, FastAPI, Next.js, APIs, databases, tool integrations, structured instructions, human approval, reliable workflows; business problems not chatbots), 4) Current Work featuring Omniveer + Duct Lead Qualifier (link omniveer.com/duct-lead-qualifier, no demo video), 5) Selected projects: Omniveer Duct Lead Qualifier, Prospector (find repo from github.com/anusbutt), Agent Replay (github.com/anusbutt/agent-replay), Nestaro Pilot (github.com/anusbutt/nestaro-pilot) — each card with problem, what it does, tags, links; TaskMate/Commit Voice only if needed for balance, 6) Skills grouped (AI systems / Backend / Frontend / Engineering / Tools), 7) compact Education (ADC Part 1 Aisha Bawany College / University of Karachi; GIAIC/PIAIC; production-oriented AI systems), 8) Contact with closing message "Have a business workflow that should be handled by an AI worker? Let's talk." preserving the working contact method; do not invent an email. - -Visual direction: premium, restrained, developer-oriented; strong typography; controlled spacing; compact cards; subtle borders; minimal animation; dark/light only if both already exist; responsive; accessible contrast and keyboard states; no giant gradients, glassmorphism, blobs, 3D gimmicks, skill bars, fake stats. - -Technical constraints: preserve framework and deployment config; reuse components; avoid dependency changes; fast and SEO-friendly; update metadata/OG/structured content; safe external links; don't delete useful assets without checking usage; don't modify unrelated config; run lint, type-check, build after editing; fix only errors caused by changes; end with summary of changed files, validation results, and content still needed. - -## Response snapshot - -1. Read full codebase (app, components, data, tailwind config, API route); confirmed no public/ assets (no hero image exists) and dark-only theme (kept dark only). -2. Found Prospector repo via GitHub search: https://github.com/anusbutt/Prospector. -3. Asked user about the custom animated cursor (recent feature vs. restraint brief) — user chose to keep it. -4. Removed IntroSequence (typing-style intro) and Scene3D (3D hero) — deleted files; page.tsx became a server component with JSON-LD Person schema; first-load JS dropped to 136 kB. -5. New components: Navbar (sticky, mobile hamburger, Omniveer external link), CurrentWork (Omniveer + Duct Lead Qualifier), Education (compact 3-item list). -6. Rewrote Hero (headline, supporting copy, availability + Pakistan status, CTAs), About copy, metadata/OG (Anus Butt — AI Engineer & Founder of Omniveer). -7. Data: 4 projects with new `problem` field and brief-specified tags/links; skills regrouped into 5 categories; socials updated (LinkedIn www URL, added Omniveer). -8. ProjectCard renders Problem line and a tidy link row; ContactForm gained the closing message and text social links; form logic and Resend route untouched. -9. Validation: `npm run lint` PASS, `npx tsc --noEmit` PASS, `npm run build` PASS. - -## Outcome - -- ✅ Impact: Portfolio repositioned around "I build AI workers for real businesses" with restrained asharib-inspired IA; Omniveer featured; bundle significantly lighter without three.js in the page -- 🧪 Tests: lint PASS, type-check PASS, production build PASS -- 📁 Files: 13 modified/created, 2 deleted (unused intro + 3D scene); no dependency changes -- 🔁 Next prompts: deploy to Vercel, consider OG image, user to confirm availability status wording and Prospector/GitHub links render as expected -- 🧠 Reflection: User's brief mapped cleanly onto the existing component architecture — data-driven sections made content swaps cheap; deleting dead files kept the diff honest. - -## Evaluation notes (flywheel) - -- Failure modes observed: none — lint/type/build clean on first pass -- Graders run and results (PASS/FAIL): ESLint PASS, tsc --noEmit PASS, next build PASS -- Prompt variant (if applicable): null -- Next experiment (smallest change to try): verify deployed OG tags with a social preview debugger after next Vercel deploy diff --git a/history/prompts/portfolio-website/005-homepage-visual-polish.refactor.prompt.md b/history/prompts/portfolio-website/005-homepage-visual-polish.refactor.prompt.md deleted file mode 100644 index 21fe9eb..0000000 --- a/history/prompts/portfolio-website/005-homepage-visual-polish.refactor.prompt.md +++ /dev/null @@ -1,60 +0,0 @@ ---- -id: 005 -title: Homepage Visual Polish -stage: refactor -date: 2026-07-18 -surface: agent -model: gpt-5 -feature: portfolio-website -branch: master -user: anusbutt -command: frontend-design -labels: ["portfolio", "visual-design", "responsive", "accessibility", "typography", "projects"] -links: - spec: null - ticket: null - adr: null - pr: null -files: - - app/globals.css - - app/page.tsx - - components/about/About.tsx - - components/contact/ContactForm.tsx - - components/education/Education.tsx - - components/hero/Hero.tsx - - components/nav/Navbar.tsx - - components/projects/ProjectCard.tsx - - components/projects/Projects.tsx - - components/skills/Skills.tsx - - components/ui/SectionHeading.tsx - - components/work/CurrentWork.tsx - - tailwind.config.ts - - history/prompts/portfolio-website/005-homepage-visual-polish.refactor.prompt.md -tests: - - npm run lint (PASS) - - npm run build (PASS; includes TypeScript validation) - - local browser visual review at 1440px and 500px widths (PASS) ---- - -## Prompt - -$frontend-design Audit and improve my portfolio homepage. Focus on visual hierarchy, typography, spacing, project presentation, responsiveness, and overall polish. Preserve all current functionality. Inspect package.json before installing anything, and run lint and build afterward. - -## Response snapshot - -Audited the existing Next.js portfolio and retained its current stack, content, links, motion, API route, and form behavior. Reworked the page into a more editorial dark visual system with a stronger hero, consistent section numbering and spacing, improved project rows, clearer capability grouping, responsive navigation, and a more polished contact section. Added form accessibility states, installed no dependencies, and validated with lint, production build, and local desktop/mobile browser renders. - -## Outcome - -- ✅ Impact: The homepage now has clearer hierarchy, more distinctive project presentation, more consistent spacing, and stronger responsive behavior while preserving all existing functionality. -- 🧪 Tests: ESLint passed; the optimized Next.js production build and TypeScript validation passed; desktop and narrow-width visual checks passed. -- 📁 Files: 13 application/config files modified and one prompt history record added; no dependencies changed. -- 🔁 Next prompts: Optionally add real project imagery or case-study detail when those assets and outcomes are available. -- 🧠 Reflection: The strongest improvement came from replacing repeated card patterns with an editorial rhythm of rules, numbered sections, and typographic contrast. - -## Evaluation notes (flywheel) - -- Failure modes observed: One mismatched JSX closing tag was caught on the first lint pass and corrected before final validation. -- Graders run and results (PASS/FAIL): ESLint PASS; Next.js build PASS; local responsive visual review PASS. -- Prompt variant (if applicable): null -- Next experiment (smallest change to try): Add one real visual artifact per featured project and compare scanability without increasing page weight materially. diff --git a/history/prompts/portfolio-website/006-commit-push-homepage-polish.misc.prompt.md b/history/prompts/portfolio-website/006-commit-push-homepage-polish.misc.prompt.md deleted file mode 100644 index 5ff787e..0000000 --- a/history/prompts/portfolio-website/006-commit-push-homepage-polish.misc.prompt.md +++ /dev/null @@ -1,46 +0,0 @@ ---- -id: 006 -title: Commit Push Homepage Polish -stage: misc -date: 2026-07-18 -surface: agent -model: gpt-5 -feature: portfolio-website -branch: master -user: anusbutt -command: github-mcp-push -labels: ["git", "github", "mcp", "commit", "push"] -links: - spec: null - ticket: null - adr: null - pr: null -files: - - history/prompts/portfolio-website/006-commit-push-homepage-polish.misc.prompt.md -tests: - - npm run lint (PASS; completed before commit) - - npm run build (PASS; completed before commit) ---- - -## Prompt - -now commit and push using mcp - -## Response snapshot - -Verified the authenticated GitHub MCP identity, repository remote, active branch, and complete working-tree scope. Committed and pushed the validated homepage polish to `anusbutt/portfolio` on `master` using the GitHub MCP server, then used a follow-up MCP commit to remove transport-only trailing CRLF bytes introduced by the first PowerShell content read. - -## Outcome - -- ✅ Impact: The completed homepage improvements and their prompt history records were committed and pushed to the configured GitHub repository. -- 🧪 Tests: The already-completed ESLint and production build validations both passed before the push. -- 📁 Files: All homepage changes and prompt history records were pushed, followed by a file-ending normalization commit containing no functional changes. -- 🔁 Next prompts: None required. -- 🧠 Reflection: Verifying MCP identity, remote ownership, branch, and diff scope before mutation kept the push precise. - -## Evaluation notes (flywheel) - -- Failure modes observed: The first MCP content upload appended a trailing CRLF to each file; a second exact-content MCP push normalized the affected endings. -- Graders run and results (PASS/FAIL): repository scope verification PASS; GitHub MCP authentication PASS -- Prompt variant (if applicable): null -- Next experiment (smallest change to try): null diff --git a/history/prompts/portfolio-website/007-full-stack-ai-positioning.refactor.prompt.md b/history/prompts/portfolio-website/007-full-stack-ai-positioning.refactor.prompt.md deleted file mode 100644 index c98a71f..0000000 --- a/history/prompts/portfolio-website/007-full-stack-ai-positioning.refactor.prompt.md +++ /dev/null @@ -1,93 +0,0 @@ ---- -id: 007 -title: Full-stack and AI Positioning -stage: refactor -date: 2026-07-18 -surface: agent -model: gpt-5 -feature: portfolio-website -branch: master -user: anusbutt -command: frontend-design -labels: ["portfolio", "positioning", "full-stack", "ai-engineering", "playwright", "navbar"] -links: - spec: null - ticket: null - adr: null - pr: null -files: - - .gitignore - - app/layout.tsx - - app/page.tsx - - components/about/About.tsx - - components/contact/ContactForm.tsx - - components/hero/Hero.tsx - - components/nav/Navbar.tsx - - components/skills/Skills.tsx - - data/skills.ts - - package.json - - package-lock.json - - playwright.config.ts - - public/Gemini_Generated_Image_6yaihi6yaihi6yai.jpg - - tests/homepage.spec.ts - - history/prompts/portfolio-website/007-full-stack-ai-positioning.refactor.prompt.md -tests: - - npm run lint (PASS) - - npm run build (PASS; includes TypeScript validation) - - npm run test:e2e (PASS; desktop Edge 1440x1000 and mobile Edge 390x844) - - Playwright screenshot review of hero, capabilities, and contact at both viewports (PASS) ---- - -## Prompt - -first add my picture in the navbar. which is in public folder and $frontend-design Update my portfolio positioning so it clearly presents me as both a full-stack developer and an AI engineer. - -Do not redesign the site. Preserve the current visual system, structure, animations, functionality, and strong Omniveer positioning. - -Update the copy strategically: - -Hero heading: -"I build full-stack web systems and practical AI products for real businesses." - -Hero description: -"From production-ready websites and dashboards to AI workflows, APIs, databases, and business automation—built end to end with Next.js, Python, FastAPI, and PostgreSQL." - -Hero tags: -- Full-stack web systems -- AI-powered products -- Business automation - -About heading: -"Building complete digital products from interface to infrastructure." - -About copy: -"I build full-stack websites, dashboards, internal tools, SaaS products, and AI-integrated systems. I work across the full product surface—from responsive Next.js interfaces and backend APIs to databases, automation, deployment, and the AI layer when it adds real value." - -Contact heading: -"Need a website, software system, or AI-powered workflow?" - -Contact copy: -"Tell me what you are building, where the current process slows down, and what a successful result should look like. I can help turn it into a complete, production-ready system." - -Also review the capabilities section and make sure full-stack website development is presented as a first-class service, not merely a supporting skill. - -Do not invent clients, metrics, testimonials, or experience. Run lint and build afterward, then use Playwright to verify the desktop and mobile layouts. - -## Response snapshot - -Added the supplied portrait to the existing navbar identity mark with `next/image` and a face-focused crop. Updated the hero, About, Contact, metadata, structured data, and capabilities copy to position full-stack development and AI engineering as equal first-class services while preserving the current design, interactions, and Omniveer section. Added `@playwright/test` as a development-only dependency plus a focused desktop/mobile responsive test using system Edge. Lint, production build, both Playwright projects, overflow assertions, and screenshot review all passed. - -## Outcome - -- ✅ Impact: The portfolio now clearly leads with full-stack web systems and practical AI products while retaining the existing Omniveer-focused visual system. -- 🧪 Tests: ESLint, optimized Next.js build, desktop Playwright, mobile Playwright, horizontal-overflow assertions, and focused screenshot review all passed. -- 📁 Files: Visible copy, metadata, capability data, navbar identity, Playwright configuration/tests, package manifests, and one prompt history record were updated or added. -- 🔁 Next prompts: Commit and push the positioning update when ready. -- 🧠 Reflection: Treating full-stack development as the first capability category made the service hierarchy clear without requiring structural or visual redesign. - -## Evaluation notes (flywheel) - -- Failure modes observed: The first Playwright run connected to a stale local preview; the next run exposed two ambiguous selectors. The stale process was scoped and stopped, selectors were tightened, and the final desktop/mobile run passed. -- Graders run and results (PASS/FAIL): ESLint PASS; Next.js build PASS; Playwright desktop PASS; Playwright mobile PASS; screenshot review PASS. -- Prompt variant (if applicable): null -- Next experiment (smallest change to try): Validate the new positioning with real portfolio visitors before changing any additional hierarchy. diff --git a/history/prompts/portfolio-website/013-ai-full-stack-hiring-positioning.refactor.prompt.md b/history/prompts/portfolio-website/013-ai-full-stack-hiring-positioning.refactor.prompt.md deleted file mode 100644 index eb5bf18..0000000 --- a/history/prompts/portfolio-website/013-ai-full-stack-hiring-positioning.refactor.prompt.md +++ /dev/null @@ -1,95 +0,0 @@ ---- -id: 013 -title: AI Full-Stack Hiring Positioning -stage: refactor -date: 2026-08-12 -surface: agent -model: gpt-5 -feature: portfolio-website -branch: master -user: user -command: Audit and update portfolio for AI Engineer and Full-stack Engineer roles -labels: [portfolio, positioning, recruiting, ai-engineering, full-stack] -links: - spec: null - ticket: null - adr: null - pr: null -files: - - app/layout.tsx - - app/page.tsx - - components/about/About.tsx - - components/contact/ContactForm.tsx - - components/education/Education.tsx - - components/hero/Hero.tsx - - components/nav/Navbar.tsx - - components/projects/ProjectCard.tsx - - components/projects/Projects.tsx - - components/skills/Skills.tsx - - components/work/CurrentWork.tsx (removed) - - data/projects.ts - - data/skills.ts - - data/socials.ts - - tests/homepage.spec.ts - - history/prompts/portfolio-website/013-ai-full-stack-hiring-positioning.refactor.prompt.md -tests: - - npm run lint (PASS) - - npm run build in isolated validation copy (PASS) - - npm run test:e2e in isolated validation copy (PASS, 2/2 desktop and mobile) - - git diff --check (PASS) - - retired-language content scan (PASS; Omniveer remains only in About and its test assertion) ---- - -## Prompt - -Audit and update my current portfolio to position me primarily for **AI Engineer and Full-stack Engineer roles**. - -The goal is recruiter/hiring-manager credibility, not selling freelance services. - -Make these changes: - -* Add **GraphKeeper** as the first and strongest featured project: - `https://github.com/anusbutt/Graph_Keeper` -* Present it around the real technical problem and engineering work: grounded/auditable memory for coding agents, evidence + provenance, Git-backed history, Codex/Claude Code integration, TypeScript CLI, validation, and open-source maintenance. -* Remove the **Omniveer Current Work** section. -* Remove **Duct Lead Qualifier** from the portfolio/projects. -* Keep Omniveer only as a short line in About mentioning that I am the **Founder of Omniveer**. -* Reposition the hero around **AI Engineer + Full-stack Engineer**, not founder/freelancer. -* Replace freelance-heavy language such as “Available for projects,” “Need a website…”, and service-selling CTAs with language appropriate for engineering roles, collaborations, and hiring. -* Add a tasteful indication that I am open to **AI Engineer and Full-stack Engineer opportunities**. -* Reorder projects so the strongest technical proof comes first: GraphKeeper, Agent Replay, Prospector, then the strongest relevant full-stack project. -* Make project descriptions concise and engineering-focused: problem, what I built, important technical decisions/capabilities, and link to proof. -* Reduce generic skills/capability filler where the projects already demonstrate those skills. -* Keep Next.js, TypeScript, Python, FastAPI, PostgreSQL, AI agents/tool use, Git/GitHub, testing, and deployment clearly discoverable. -* Preserve the existing visual quality and overall design language; improve positioning and content hierarchy rather than redesigning unnecessarily. -* Optimize the page so a technical recruiter can understand within ~30 seconds: - - 1. what kind of engineer I am, - 2. what I can build, - 3. evidence that I actually ship, - 4. how to contact me. - -Also inspect the existing site critically and make any small content/hierarchy improvements that materially strengthen my chances for AI Engineer or Full-stack Engineer roles. - -Keep all claims factual and supported by the projects. - -Afterward, summarize the sections changed and why each change improves hiring signal. - -## Response snapshot - -Repositioned the portfolio around AI Engineer and Full-stack Engineer hiring. Moved selected engineering work directly below the hero, added GraphKeeper as the visually dominant first project, reordered the remaining proof as Agent Replay, Prospector, and Commit Voice, and rewrote all project copy from verified public repository evidence. Removed the Omniveer Current Work component, Duct Lead Qualifier, founder-first metadata/navigation, and service-selling calls to action. Reduced the skills section to three focused groups and changed Contact to invite roles and technical collaborations. Updated responsive end-to-end coverage and verified lint, an isolated production build, and desktop/mobile tests. - -## Outcome - -- ✅ Impact: Recruiters now see role identity, technical proof, shipped source links, focused stack, availability, and contact path in a clear evidence-first sequence. -- 🧪 Tests: ESLint passed; clean production build passed in an isolated copy; Playwright passed 2/2 desktop and mobile checks. -- 📁 Files: 14 source/test files changed, one obsolete component removed, and this PHR added. -- 🔁 Next prompts: Review the deployed page and adjust only if new project evidence or role targets change. -- 🧠 Reflection: Selecting Commit Voice as the fourth project preserved explicit full-stack proof through Next.js, TypeScript, PostgreSQL, auth, API integrations, scheduled work, and deployment. - -## Evaluation notes (flywheel) - -- Failure modes observed: The Windows sandbox helper was unavailable; an existing project dev server raced with the local `.next` build cache; the in-app browser runtime assets were missing. -- Graders run and results (PASS/FAIL): Content/evidence audit PASS; lint PASS; production build PASS in isolated copy; responsive E2E PASS; diff whitespace check PASS. -- Prompt variant (if applicable): none -- Next experiment (smallest change to try): Measure recruiter comprehension with a five-second test after deployment before changing visual design. diff --git a/history/prompts/portfolio-website/014-commit-push-portfolio-update.misc.prompt.md b/history/prompts/portfolio-website/014-commit-push-portfolio-update.misc.prompt.md deleted file mode 100644 index ad05c69..0000000 --- a/history/prompts/portfolio-website/014-commit-push-portfolio-update.misc.prompt.md +++ /dev/null @@ -1,47 +0,0 @@ ---- -id: 014 -title: Commit Push Portfolio Update -stage: misc -date: 2026-08-13 -surface: agent -model: gpt-5 -feature: portfolio-website -branch: master -user: user -command: Commit and push the completed portfolio update -labels: [git, commit, push, portfolio] -links: - spec: null - ticket: null - adr: null - pr: null -files: - - history/prompts/portfolio-website/014-commit-push-portfolio-update.misc.prompt.md -tests: - - git diff --cached --check - - git status --short - - git push origin master ---- - -## Prompt - -now commit and push. - -## Response snapshot - -Staged the scoped AI Engineer and Full-stack Engineer portfolio update and its prompt-history records. The repository's GraphKeeper pre-commit hook blocked commit creation because its untracked baseline graph files were not staged; requested the user's choice before either expanding the commit scope or explicitly bypassing the hook. - -## Outcome - -- ✅ Impact: Prepared a verified, narrowly scoped staged change set without committing unrelated files. -- 🧪 Tests: Reused the already-passing lint, clean production build, and desktop/mobile Playwright results; staged diff validation passed; GraphKeeper hook reported GK101 for three unstaged baseline files. -- 📁 Files: Scoped portfolio source, test, and PHR files only; unrelated untracked files excluded. -- 🔁 Next prompts: Choose whether to include the GraphKeeper baseline files or bypass the hook for this portfolio-only commit. -- 🧠 Reflection: Explicit path staging avoided accidentally committing pre-existing untracked repository artifacts. - -## Evaluation notes (flywheel) - -- Failure modes observed: The working tree contained unrelated untracked files; local master was four commits ahead of origin; GraphKeeper first required jq, then required its untracked baseline JSON files to be staged. -- Graders run and results (PASS/FAIL): Staged diff validation PASS; GraphKeeper hook FAIL (GK101); commit and push not yet performed. -- Prompt variant (if applicable): none -- Next experiment (smallest change to try): Add a repository ignore policy for local agent artifacts only if the project owner wants them permanently excluded. diff --git a/history/prompts/portfolio-website/015-include-graphkeeper-baseline.misc.prompt.md b/history/prompts/portfolio-website/015-include-graphkeeper-baseline.misc.prompt.md deleted file mode 100644 index 5012e17..0000000 --- a/history/prompts/portfolio-website/015-include-graphkeeper-baseline.misc.prompt.md +++ /dev/null @@ -1,50 +0,0 @@ ---- -id: 015 -title: Include GraphKeeper Baseline -stage: misc -date: 2026-08-13 -surface: agent -model: gpt-5 -feature: portfolio-website -branch: master -user: user -command: Include required GraphKeeper baseline files and continue commit and push -labels: [git, graphkeeper, commit, push] -links: - spec: null - ticket: null - adr: null - pr: null -files: - - graph/entities.json - - graph/claims.json - - graph/runs.json - - history/prompts/portfolio-website/015-include-graphkeeper-baseline.misc.prompt.md -tests: - - GraphKeeper pre-commit validation - - git diff --cached --check - - git push origin master ---- - -## Prompt - -include - -## Response snapshot - -Included the three GraphKeeper baseline JSON files required by the repository hook, kept the remaining unrelated untracked files excluded, committed the scoped portfolio update, and pushed master to origin. - -## Outcome - -- ✅ Impact: Unblocked the repository validation contract while preserving a narrow commit scope. -- 🧪 Tests: GraphKeeper hook and staged diff checks passed before push. -- 📁 Files: Added the three required baseline JSON files and this continuation PHR alongside the already staged portfolio update. -- 🔁 Next prompts: Confirm the deployment completed if desired. -- 🧠 Reflection: Including only the hook-required baseline files avoided absorbing unrelated GraphKeeper support files. - -## Evaluation notes (flywheel) - -- Failure modes observed: GraphKeeper required baseline JSON files in every validated commit after initialization. -- Graders run and results (PASS/FAIL): GraphKeeper hook PASS; Git push result reported by Git. -- Prompt variant (if applicable): none -- Next experiment (smallest change to try): Commit the remaining GraphKeeper installation files separately only if the project owner wants full repository integration. diff --git a/history/prompts/portfolio-website/017-restructure-full-stack-ai-projects.refactor.prompt.md b/history/prompts/portfolio-website/017-restructure-full-stack-ai-projects.refactor.prompt.md deleted file mode 100644 index 726c1a6..0000000 --- a/history/prompts/portfolio-website/017-restructure-full-stack-ai-projects.refactor.prompt.md +++ /dev/null @@ -1,83 +0,0 @@ ---- -id: 017 -title: Restructure Full-stack AI Projects -stage: refactor -date: 2026-08-13 -surface: agent -model: GPT-5 -feature: portfolio-website -branch: master -user: portfolio-owner -command: Update portfolio Selected Work positioning -labels: [portfolio, projects, full-stack-ai, positioning] -links: - spec: specs/portfolio-website/spec.md - ticket: null - adr: null - pr: null -files: - - data/projects.ts - - components/projects/Projects.tsx - - components/projects/ProjectCard.tsx - - tests/homepage.spec.ts - - history/prompts/portfolio-website/017-restructure-full-stack-ai-projects.refactor.prompt.md -tests: - - npm run lint (PASS) - - npm run build (PASS) - - npm run test:e2e (PASS, desktop-edge and mobile-edge) - - git diff --check (PASS) - - Playwright screenshot inspection at 1440x1000 and 390x844 (PASS) ---- - -## Prompt - -Update my portfolio at `anasbutt.site` to better position me as a **Full-stack AI Engineer**. - -Restructure the **Selected Work / Projects** section instead of just adding more cards. - -Use this order: - -1. **GraphKeeper** — make this the flagship project - Repo: https://github.com/anusbutt/Graph_Keeper - Position it around durable, auditable memory for coding agents, evidence-backed claims, Git-native storage, and agent reliability. - -2. **TaskMate** - Repo: https://github.com/anusbutt/taskmate - Position it as a full-stack AI task manager where users can create, update, complete, and delete tasks through natural language. Highlight Next.js, FastAPI, PostgreSQL, auth, AI agents, and MCP/tool actions. - -3. **Omniveer Duct Lead Qualifier** - Keep it, but make the description concise and focused on applied AI automation for real business workflows. - -4. **RAG-Powered Interactive Robotics Textbook** - Repo: https://github.com/anusbutt/Physical-AI-Humanoid-Robotics-Textbook - Do not frame me primarily as a robotics engineer. Focus on the engineering: RAG, embeddings, Qdrant/vector search, source-grounded answers, citations, FastAPI, and deployed interactive learning. - -5. **Agent Replay** - Keep it and emphasize AI-agent debugging, observability, and verification. - -Remove **Nestaro Pilot** from the main portfolio. Move **Prospector** to a smaller “More Projects” section if appropriate. - -Keep the design minimal and consistent with the current portfolio. Improve hierarchy rather than adding clutter. For each main project, prefer concise copy, clear tech tags, GitHub/demo links where available, and a screenshot or visual only if it genuinely improves the card. - -Also update any introductory project-section copy so it reflects **AI agents, full-stack AI systems, developer tooling, RAG, and production automation** rather than mainly lead-generation/business automation. - -Do not redesign the entire site or change unrelated sections. - -## Response snapshot - -Restructured Selected Work into five ordered primary projects with GraphKeeper as the visually distinct flagship, added verified live/source links and concise engineering-focused copy, moved Prospector into a compact More Projects row, removed Nestaro from main work, and updated responsive acceptance coverage. No dependencies or project screenshots were added. - -## Outcome - -- ✅ Impact: Portfolio now foregrounds Full-stack AI engineering across agent memory, agentic products, applied automation, RAG, and observability. -- 🧪 Tests: Lint, production build, desktop/mobile Playwright tests, diff checks, and screenshot review passed. -- 📁 Files: Four application/test files changed plus this PHR. -- 🔁 Next prompts: Review and deploy the focused portfolio update when ready. -- 🧠 Reflection: Existing editorial rows were retained; hierarchy improved through ordering, copy, restrained flagship emphasis, and a smaller secondary-project treatment. - -## Evaluation notes (flywheel) - -- Failure modes observed: The first e2e run exposed a stale page-wide assertion that conflicted with restoring the Omniveer project; it was correctly narrowed to the contact section. The in-app browser had no available instance, so passing Playwright screenshots were inspected directly. -- Graders run and results (PASS/FAIL): ESLint PASS; Next.js build/type check PASS; Playwright desktop PASS; Playwright mobile PASS; visual screenshot review PASS. -- Prompt variant (if applicable): none -- Next experiment (smallest change to try): Gather hiring-manager feedback on whether the flagship copy communicates agent reliability within one scan. diff --git a/history/prompts/portfolio-website/018-commit-push-portfolio-update.misc.prompt.md b/history/prompts/portfolio-website/018-commit-push-portfolio-update.misc.prompt.md deleted file mode 100644 index f7e2205..0000000 --- a/history/prompts/portfolio-website/018-commit-push-portfolio-update.misc.prompt.md +++ /dev/null @@ -1,59 +0,0 @@ ---- -id: 018 -title: Commit Push Portfolio Update -stage: misc -date: 2026-08-13 -surface: agent -model: GPT-5 -feature: portfolio-website -branch: refactor/full-stack-ai-projects -user: portfolio-owner -command: git commit and push -labels: [git, commit, push, portfolio] -links: - spec: specs/portfolio-website/spec.md - ticket: null - adr: null - pr: null -files: - - components/projects/ProjectCard.tsx - - components/projects/Projects.tsx - - data/projects.ts - - evidence/portfolio-project-hierarchy.txt - - graph/claims.json - - graph/entities.json - - graph/runs.json - - tests/homepage.spec.ts - - history/prompts/general/016-load-repository-agent-rules.general.prompt.md - - history/prompts/portfolio-website/017-restructure-full-stack-ai-projects.refactor.prompt.md - - history/prompts/portfolio-website/018-commit-push-portfolio-update.misc.prompt.md -tests: - - npm run lint (PASS before Git workflow) - - npm run build (PASS before Git workflow) - - npm run test:e2e (PASS, desktop-edge and mobile-edge, before Git workflow) - - bash scripts/validate.sh --worktree (PASS before Git workflow) - - git diff --check (PASS before Git workflow) ---- - -## Prompt - -now commit and push - -## Response snapshot - -Executed the requested Git workflow for the focused Full-stack AI portfolio update on a dedicated feature branch, with explicit staging that excluded unrelated pre-existing untracked files. Final commit, push, and remote details are reported in the assistant response. - -## Outcome - -- ✅ Impact: The verified portfolio project hierarchy and supporting records are grouped into a reviewable Git change. -- 🧪 Tests: Existing lint, build, responsive e2e, GraphKeeper, and diff-integrity checks were already passing before the Git-only workflow. -- 📁 Files: Portfolio data/components, responsive test, GraphKeeper provenance, and required PHRs are included. -- 🔁 Next prompts: Review or merge the remote branch when ready. -- 🧠 Reflection: Explicit path staging protects unrelated user-owned work in the dirty worktree. - -## Evaluation notes (flywheel) - -- Failure modes observed: The PHR helper allocated colliding ID 0001; the record was corrected to the next valid ID, 018, before staging. -- Graders run and results (PASS/FAIL): PHR route, prompt completeness, placeholder validation, and Git remote verification PASS; GitHub CLI unavailable, so the manual PR URL is reported. -- Prompt variant (if applicable): none -- Next experiment (smallest change to try): none diff --git a/specs/portfolio-architecture-refactor/PROGRESS.md b/specs/portfolio-architecture-refactor/PROGRESS.md deleted file mode 100644 index f309cf7..0000000 --- a/specs/portfolio-architecture-refactor/PROGRESS.md +++ /dev/null @@ -1,70 +0,0 @@ -# Portfolio Architecture Refactor Progress - -**Last updated**: 2026-08-13 -**Status**: Complete — implementation and validation finished -**Current task**: T013 — Final architectural review and handoff - -## Completed work - -- [x] Audited the App Router, source tree, content, API, dependencies, TypeScript, - ESLint, Playwright, environment files, assets, metadata, history, evidence, - graph, GitHub configuration, README, Git history, and secret-like patterns. -- [x] Wrote and followed the fresh SDD specification, plan, and ordered task list. -- [x] Migrated application code to src/app, src/components, src/content, and - src/server without leaving duplicate root application directories. -- [x] Centralized profile, projects, skills, socials, and education content. -- [x] Upgraded to Next.js 16.3.0 and React 19.2.8; modernized flat ESLint and scripts. -- [x] Removed unused React Three Fiber, Drei, and Three dependencies. -- [x] Added runtime contact validation, honeypot handling, bounded in-memory rate - limiting, fixed-recipient email service, environment-driven configuration, and - predictable 400/429/502/503 responses. -- [x] Reduced client boundaries to navigation, contact form, and custom cursor; static - page sections remain Server Components. -- [x] Added canonical metadata, Open Graph/Twitter metadata, robots, sitemap, and a - deliberate public/logo.png asset name. -- [x] Replaced the template README and added CI, MIT license, contributing, security, - and editor configuration files. -- [x] Added Playwright coverage for responsive homepage behavior, contact errors, and - SEO routes. -- [x] Reviewed public-repository development records. Existing .claude, .specify, - history, evidence, and graph records remain because they are required SDD/ - provenance artifacts and contain no discovered live secrets. -- [x] Validated GraphKeeper with bash scripts/validate.sh --worktree. - -## Validation results - -- [x] npm run lint — PASS -- [x] npm run typecheck — PASS -- [x] npm run build — PASS -- [x] npm run test:e2e — PASS (10 tests on desktop/mobile Chromium) -- [x] npm run check — PASS -- [x] bash scripts/validate.sh --worktree — PASS -- [ ] npm ci — the Windows package process exceeded the five-minute tool budget; - the subsequent package state passed all npm quality gates and browser tests. -- [x] Secret-like scan — no live credential found; only the documented .env.example - placeholder and an unrelated template word in historical instructions matched. - -## Important decisions - -- Preserve the current dark editorial visual identity, section IDs, copy, links, and - evidence-backed project hierarchy; do not reintroduce the unused 3D feature. -- Use a small src/server boundary rather than enterprise layers. -- Use an in-memory limiter suitable for low-volume portfolio traffic; document its - per-instance limitation and revisit only if abuse volume warrants a managed service. -- Keep Resend but make API key, verified sender, recipient, and site URL configurable. -- Keep .claude, .specify, history, evidence, and graph as intentional development/ - provenance artifacts instead of deleting them blindly. - -## Remaining limitations - -- The in-memory limiter does not coordinate across multiple Vercel instances and resets - during deployment. -- The form provider requires production Resend configuration and verified sender setup. -- The existing repository history includes earlier development records; they are - retained for traceability rather than presented as product runtime code. - -## Resume instructions - -The refactor is complete. For future changes, read this progress file and the feature -specification before modifying architecture; update the SDD artifacts first when scope -changes. \ No newline at end of file diff --git a/specs/portfolio-architecture-refactor/plan.md b/specs/portfolio-architecture-refactor/plan.md deleted file mode 100644 index 7ea0daf..0000000 --- a/specs/portfolio-architecture-refactor/plan.md +++ /dev/null @@ -1,149 +0,0 @@ -# Portfolio Architecture Refactor Plan - -## 1. Scope and dependencies - -### In scope - -Incrementally migrate the existing portfolio into `src/`, centralize its current -content, isolate the contact server boundary, modernize project tooling, add SEO and -public-repository documentation, and validate the unchanged visual experience. - -### Out of scope - -Visual redesign, new features such as 3D, auth, CMS, analytics, external rate limiting, -or a wholesale component rewrite. - -### External dependencies - -- Next.js/React and npm registry: framework and package compatibility. -- Resend: contact email delivery, configured by the site owner. -- Vercel: production hosting and environment variables. -- GitHub Actions: CI execution and browser dependencies. -- Microsoft Edge/Playwright Chromium availability: local browser validation. - -## 2. Target architecture - -```text -public/ -src/ - app/ - api/contact/route.ts - layout.tsx - page.tsx - globals.css - robots.ts - sitemap.ts - components/ - sections/ # server-rendered section shells - layout/ # navigation/footer - ui/ # focused reusable primitives - client/ # small state/effect islands - content/ - profile.ts - projects.ts - skills.ts - socials.ts - education.ts - server/contact/ - validation.ts - rate-limit.ts - service.ts - server/email/ - resend.ts -tests/e2e/ -.github/workflows/ci.yml -``` - -The existing design components move with minimal semantic changes. The server -section shells import canonical content and render it; motion is delegated to small -client wrappers rather than turning every section into a client boundary. - -## 3. Ordered implementation map - -| Step | Requirement | Concrete changes | Validation | -|---|---|---|---| -| 1 | R1, R3 | Add `src/` tree, move content and app/component files, update alias and Tailwind content globs | Typecheck, import scan, homepage smoke test | -| 2 | R5 | Verify stable package versions, remove unused 3D packages, add flat ESLint and scripts | `npm ci`, lint, typecheck | -| 3 | R4 | Add runtime validator, bounded in-memory limiter, contact service, server-only Resend adapter, env docs | Unit-level route checks and API/browser behavior | -| 4 | R2 | Convert static sections to Server Components and retain only focused client islands | Build plus source boundary audit | -| 5 | R6 | Add canonical profile metadata, robots, sitemap, rename logo, add safe site URL helper | Build and route/content assertions | -| 6 | R7 | Replace README, add CI and appropriate public-repo files, update Playwright config/tests | Markdown/config review and CI-equivalent local commands | -| 7 | All | Run final checks, inspect generated output, update progress and report limitations | Full validation matrix | - -## 4. Migration details and compatibility risks - -### Files to add - -- `src/content/*` canonical content modules. -- `src/server/contact/*` and `src/server/email/*` server boundary modules. -- `src/app/robots.ts`, `src/app/sitemap.ts`. -- `eslint.config.mjs`, `.github/workflows/ci.yml`, `PROGRESS.md`, and relevant docs. -- Additional focused tests for contact validation/limiting if the chosen test setup - supports them without adding unnecessary dependencies. - -### Files to change - -- `package.json` and lockfile, `tsconfig.json`, `next.config.*`, Tailwind config, - Playwright config, `.env.example`. -- `src/app/layout.tsx`, `src/app/page.tsx`, `src/app/globals.css`. -- Existing sections, navigation, cursor, and form after migration. -- README and tracked project guidance where it describes stale structure. - -### Files to remove or relocate - -- Root `app/`, `components/`, `data/`, and `lib/` after their contents are migrated. -- `.eslintrc.json` after flat config is in place. -- Unused 3D packages and the misspelled duplicate-extension asset name. -- No SDD/history/evidence/graph file is removed without a separate rationale. - -### Compatibility risks - -1. A major Next.js/React upgrade may change lint, metadata, or font behavior. Verify - the exact supported pair first and use the lockfile. -2. Moving the alias to `src/*` can leave stale imports. Use a complete import scan and - TypeScript build before deleting root duplicates. -3. Making sections server-rendered can change animation timing. Preserve the existing - visual transition through small client wrappers and test reduced motion. -4. In-memory rate limiting is per instance and resets on deploy. Document this - intentional low-traffic portfolio tradeoff; a managed limiter is a future option. -5. `metadataBase` depends on an environment URL. Use a deterministic default and - document the deployment override. - -## 5. Behavior preservation strategy - -- Keep current copy, project order, URLs, section IDs, color tokens, spacing language, - and mobile menu behavior. -- Keep the custom cursor as an optional desktop-only client island and preserve the - coarse-pointer fallback. -- Keep form field names, validation limits, success text, and error-state input - preservation while improving server validation and configuration. -- Keep `framer-motion` only where it materially supports existing entrance/cursor - behavior; do not add a new motion system. - -## 6. Validation gates - -1. After migration: imports, typecheck, and no duplicate root source. -2. After tooling/dependency update: clean install, lint, typecheck, and build. -3. After contact refactor: malformed-body, validation, limiter, missing-config, and - provider-error checks, plus form preservation in the browser. -4. After SEO/docs/CI: metadata route and source scans, README/config review. -5. Final: `npm ci`, lint, typecheck, build, `check`, e2e, responsive overflow, mobile - navigation, anchor links, robots, sitemap, and secret scan. - -## 7. Operational readiness - -- Log only server-side error categories and request correlation context that contains - no message body or secret. -- Return `429` with `Retry-After` for limiter rejection and generic `5xx` responses for - configuration/provider failures. -- Vercel environment variables are the production source of truth. -- Roll back through the previous Git/Vercel deployment if the contact provider or build - fails. -- CI is the required merge gate; no deployment automation is added in this task. - -## 8. Architectural decision checkpoint - -The framework/tooling upgrade, `src/` migration, and server/client boundary are -cross-cutting decisions with long-term consequences and multiple viable options. -They should be offered as one grouped ADR after implementation validation rather than -created automatically. diff --git a/specs/portfolio-architecture-refactor/spec.md b/specs/portfolio-architecture-refactor/spec.md deleted file mode 100644 index 24a16e2..0000000 --- a/specs/portfolio-architecture-refactor/spec.md +++ /dev/null @@ -1,183 +0,0 @@ -# Portfolio Architecture Refactor Specification - -**Feature**: `portfolio-architecture-refactor` -**Status**: Implemented and validated -**Date**: 2026-08-13 -**Source**: `Codex Prompt — Portfolio Architecture Refactor with Pure SDD.md` - -## 1. Context and current-state findings - -The repository is a working Next.js portfolio on the `refactor/full-stack-ai-projects` -branch. Its current visual identity is a dark, editorial portfolio with white text, -orange accents, grid texture, responsive navigation, project hierarchy, skills, -education, social links, and a Resend-backed contact form. The refactor must preserve -that identity and the current content hierarchy. - -The audit found: - -- App Router files and reusable components currently live at repository root. -- Portfolio content is split across `data/` and component-local constants. -- Several whole sections are Client Components only to use Framer Motion. -- The contact route casts `request.json()` directly, hard-codes sender/recipient - values, and has no abuse protection. -- Tooling uses Next 14's legacy `.eslintrc.json` and `next lint` script. -- There are no `robots.ts`, `sitemap.ts`, CI workflow, or professional README. -- `public/logo.png.png` is a suspiciously named asset referenced by metadata and nav. -- React Three Fiber/Three dependencies are installed but not used by the current app. -- Existing GraphKeeper evidence records five primary projects and Prospector as a - secondary project; those entries are authoritative for the content migration. -- The baseline lint/typecheck command exceeded the two-minute execution budget before - returning a result; this is not considered a pass. - -## 2. Scope - -### In scope - -1. Move the application to a clear `src/` App Router structure without changing the - rendered design or portfolio content unless correctness, accessibility, security, - or maintainability requires it. -2. Establish a canonical server-safe content layer for profile, projects, skills, - socials, and education. -3. Reduce client JavaScript to focused islands for navigation, form state, cursor, - and viewport animation behavior. Static section shells and data rendering remain - Server Components. -4. Refactor the contact endpoint into route → validation → abuse protection → - application function → Resend adapter, with predictable errors and environment - configuration. -5. Modernize dependencies and tooling to a currently supported stable Next.js/React - stack after verifying exact versions from authoritative package sources. -6. Add App Router metadata, canonical URL handling, `robots.ts`, and `sitemap.ts`. -7. Add a useful quality gate, CI, responsive/accessibility tests, and repository - documentation. -8. Audit public-repository hygiene and secret-like content without publishing - credentials or deleting useful project history blindly. - -### Out of scope - -- A visual redesign, new portfolio sections, new projects, new 3D experience, or a - replacement animation system. -- A database, authentication system, external rate-limit service, CMS, analytics - integration, or generic email relay. -- Rewriting working visual components solely to make the diff larger. -- Deleting `.specify/`, `history/`, `evidence/`, or `graph/` without an explicit - public-repository policy decision and evidence review. -- Production deployment or changing Vercel project settings. - -## 3. Functional requirements - -### R1 — Repository architecture - -- The final application uses `src/app`, `src/components`, `src/content`, and - `src/server` boundaries. -- The contact route is at `src/app/api/contact/route.ts`. -- Existing imports use the `@/` alias and the alias resolves to `src/*`. -- Component names and existing section IDs remain stable unless a correctness fix - requires a change. - -### R2 — Server-first rendering - -- `src/app/page.tsx`, static section components, content modules, layout, and SEO - routes are Server Components. -- Client Components are limited to browser state/effects: mobile menu, contact form, - custom cursor, and small viewport animation wrappers where needed. -- No Redux, dependency injection, repository layer, or other enterprise abstraction is - introduced. -- Static portfolio text is present in the server-rendered HTML. -- `prefers-reduced-motion` disables or minimizes nonessential motion. - -### R3 — Canonical content - -- A single content module owns identity/metadata values used by layout, hero, footer, - and structured data. -- Projects preserve the current five primary projects and Prospector as secondary, - including links, descriptions, problem statements, and technology lists. -- Skills, socials, and education move into the same canonical content boundary. -- No secret, API key, or deployment-only value is stored in content modules. - -### R4 — Contact boundary - -- The route accepts only a JSON object with `name`, `email`, `message`, and an - optional honeypot field; unknown or malformed JSON returns a predictable `400`. -- Server validation trims and bounds fields, validates email syntax, and never trusts - a TypeScript cast as runtime validation. -- A honeypot submission is rejected without sending mail. -- A lightweight per-process, bounded-window limiter prevents repeated submissions from - one IP. The implementation must fail closed for the limiter's own malformed input - but must not crash the route. -- Sender address, recipient address, and public site URL are environment-driven; - `RESEND_API_KEY` remains server-only. -- Missing configuration returns a generic `503` response and logs diagnostic detail - only on the server. -- Resend failures return a generic `502` response; validation returns `400`; a - limited request returns `429` with `Retry-After`; success returns `200` with the - same stable success shape. -- The endpoint sends only the portfolio contact message and cannot be used to choose - arbitrary recipients, sender addresses, or headers. - -### R5 — Tooling and dependencies - -- `npm run dev`, `npm run build`, `npm run lint`, `npm run typecheck`, - `npm run test:e2e`, and `npm run check` are available. -- ESLint uses flat config and does not depend on the removed `next lint` command. -- TypeScript remains strict with no unjustified `any`. -- Unused React Three Fiber, Drei, and Three packages are removed because the current - app does not use them and reintroducing a 3D feature is out of scope. -- Package upgrades are deliberate, lockfile-backed, and verified against the chosen - Next.js/React compatibility range. - -### R6 — Metadata and public assets - -- `metadataBase`, canonical URL, title, description, Open Graph, Twitter card, and - icon references are valid for the configured site URL. -- `src/app/robots.ts` and `src/app/sitemap.ts` are present and use the canonical site - URL. -- The double-extension logo asset is renamed to a deliberate filename and all - references are updated. -- No untrusted content is injected into the page as HTML. - -### R7 — Repository hygiene and documentation - -- README explains purpose, architecture, stack, setup, environment variables, - commands, tests, deployment, and important decisions without template boilerplate. -- `.env.example` documents every required variable with safe placeholders and no - live secret. -- A CI workflow runs clean install, lint, typecheck, build, and the browser checks - where the runner supports them. -- Add only open-source completeness files that make sense for this portfolio. A - permissive license is included only if the repository's public intent supports it; - private agent history remains clearly separated from production source. - -## 4. Acceptance criteria - -- [ ] The final source tree has the planned `src/` boundaries and no stale duplicate - application/content tree remains. -- [ ] The homepage preserves current headings, project order, section IDs, links, - dark/orange design, responsive navigation, and contact interaction. -- [ ] Static content is server-rendered and client boundaries are limited and - explainable. -- [ ] Contact requests with non-object JSON, missing fields, invalid email, oversized - fields, honeypot input, repeated IP submissions, missing configuration, and - provider failure follow the specified error taxonomy. -- [ ] No secret-like value is tracked or emitted to the client bundle. -- [ ] `npm ci`, `npm run lint`, `npm run typecheck`, `npm run build`, `npm run check`, - and `npm run test:e2e` are run and results are recorded. -- [ ] Metadata, favicon, robots, sitemap, internal anchors, mobile layout, and - horizontal-overflow checks pass. -- [ ] README, CI, environment documentation, and progress report describe the final - architecture and intentional tradeoffs. - -## 5. Error and compatibility constraints - -The refactor must not expose whether an email address is configured, leak provider -errors, or accept arbitrary Resend fields. If the production site URL is unavailable -at build time, metadata and sitemap generation must use a documented safe default and -remain deterministic. If a browser does not support a motion API, the content and -navigation remain usable. If an external email provider is unavailable, the form -retains user input and reports a retryable generic error. - -## 6. Definition of done - -The repository is considered done when the implementation, documentation, CI, and -verification results satisfy all acceptance criteria, the final review finds no clear -stale architecture or secret exposure, and `PROGRESS.md` records remaining intentional -limitations. diff --git a/specs/portfolio-architecture-refactor/tasks.md b/specs/portfolio-architecture-refactor/tasks.md deleted file mode 100644 index 9b3c5c0..0000000 --- a/specs/portfolio-architecture-refactor/tasks.md +++ /dev/null @@ -1,123 +0,0 @@ -# Portfolio Architecture Refactor Tasks - -Tasks are ordered. Each task records its objective, affected files, dependency, and -validation so another session can resume without reconstructing the plan. - -## Phase 0 — SDD gate - -- [x] **T001 — Write fresh SDD artifacts** - - Objective: Define final-state requirements, architecture, risks, and acceptance checks. - - Files: `spec.md`, `plan.md`, `tasks.md`, `PROGRESS.md`. - - Depends on: repository audit. - - Validation: all three artifacts agree on scope; no application code changed. - -## Phase 1 — Source and content migration - -- [x] **T002 — Create the `src/` boundaries** - - Objective: Move App Router, components, data, and server utility code into the - planned source tree with minimal behavior changes. - - Files: `src/app/**`, `src/components/**`, `src/content/**`, `src/server/**`, - `tsconfig.json`, `tailwind.config.ts`. - - Depends on: T001. - - Validation: no root source duplicates; import scan and typecheck pass. - -- [x] **T003 — Centralize canonical content** - - Objective: Move profile, project, skill, social, and education values into typed - content modules and update all consumers. - - Files: `src/content/*.ts`, sections, layout, structured data. - - Depends on: T002. - - Validation: current five primary projects plus Prospector render in order; no - duplicated identity constants outside content. - -## Phase 2 — Tooling and dependency modernization - -- [x] **T004 — Select and apply supported package versions** - - Objective: Verify the supported Next.js/React pair and update package manifests; - remove unused Three/R3F packages. - - Files: `package.json`, `package-lock.json`, `next.config.*`. - - Depends on: T002. - - Validation: clean `npm ci`, dependency import audit, build. - -- [x] **T005 — Replace legacy lint and scripts** - - Objective: Add flat ESLint config and predictable scripts for lint, typecheck, e2e, - and the composite check. - - Files: `eslint.config.mjs`, `package.json`, Playwright config. - - Depends on: T004. - - Validation: each script runs with a clear exit code; `npm run lint` passes. - -## Phase 3 — Secure contact boundary - -- [x] **T006 — Implement runtime contact validation and abuse protection** - - Objective: Add unknown-input validation, honeypot handling, bounded in-memory - limiter, and error taxonomy. - - Files: `src/server/contact/validation.ts`, `src/server/contact/rate-limit.ts`, - `src/app/api/contact/route.ts`. - - Depends on: T002. - - Validation: malformed, invalid, oversized, honeypot, and repeated requests return - expected statuses without sending mail. - -- [x] **T007 — Isolate the email adapter and configuration** - - Objective: Keep Resend server-only, move from/to/site URL to environment variables, - and make provider/configuration failures generic to clients. - - Files: `src/server/contact/service.ts`, `src/server/email/resend.ts`, `.env.example`. - - Depends on: T006. - - Validation: missing config is `503`, provider failure is `502`, success has stable - response shape, no secret is bundled. - -## Phase 4 — Server/client and SEO boundaries - -- [x] **T008 — Reduce unnecessary client boundaries** - - Objective: Keep page, layout, static sections, and content server-rendered; retain - only navigation/form/cursor and small motion islands. - - Files: `src/app/page.tsx`, `src/components/**`. - - Depends on: T003, T007. - - Validation: source audit of `"use client"`; build; reduced-motion and JS-off behavior. - -- [x] **T009 — Add metadata routes and correct public asset naming** - - Objective: Add metadataBase/canonical/Open Graph/Twitter, robots, sitemap, and fix - the double-extension logo reference. - - Files: `src/app/layout.tsx`, `src/app/robots.ts`, `src/app/sitemap.ts`, `public/*`. - - Depends on: T003. - - Validation: build plus route/content checks for metadata, robots, and sitemap. - -## Phase 5 — Public project quality - -- [x] **T010 — Add README, CI, and public-repo completeness** - - Objective: Replace template documentation, add CI, and include only appropriate - governance files. - - Files: `README.md`, `.github/workflows/ci.yml`, `.editorconfig`, `LICENSE` as - justified, and tracked guidance updates. - - Depends on: T005, T009. - - Validation: documentation review; CI commands match local scripts. - -- [x] **T011 — Expand browser and API acceptance tests** - - Objective: Cover current content hierarchy, mobile nav, overflow, metadata routes, - contact errors, and form input preservation without redesigning the test suite. - - Files: `tests/e2e/**`, any focused test helpers. - - Depends on: T007, T009. - - Validation: Playwright on desktop/mobile and relevant route checks. - -## Phase 6 — Final validation and review - -- [x] **T012 — Run the complete verification matrix** - - Objective: Execute clean install, lint, typecheck, build, check, e2e, secret scan, - and internal-link/unused-source review. - - Files: `PROGRESS.md`, evidence/log files if needed. - - Depends on: T002–T011. - - Validation: record exact commands and results; failures remain explicit. - -- [x] **T013 — Final architectural review and handoff** - - Objective: Review the final tree as a public repository, remove only clearly stale - in-scope files, update progress, and report tradeoffs. - - Files: `PROGRESS.md`, any final scoped cleanup files. - - Depends on: T012. - - Validation: acceptance checklist complete or limitations documented. - -## Dependency graph - -```text -T001 → T002 → T003 ─┐ - ├→ T004 → T005 ─┐ - ├→ T006 → T007 ─┼→ T008 → T009 → T010 → T011 → T012 → T013 - └────────────────┘ -``` diff --git a/specs/portfolio-website/plan.md b/specs/portfolio-website/plan.md deleted file mode 100644 index 180fe7f..0000000 --- a/specs/portfolio-website/plan.md +++ /dev/null @@ -1,216 +0,0 @@ -# Implementation Plan: Anus Yousuf Portfolio Website - -**Branch**: `001-portfolio-website` | **Date**: 2026-06-23 | **Spec**: [spec.md](./spec.md) -**Input**: Feature specification from `/specs/portfolio-website/spec.md` - -## Summary - -Build a dark-themed personal portfolio website for Anus Yousuf using Next.js 14 App Router. The site features an intro text-slam animation sequence, an interactive 3D hero scene (React Three Fiber), project showcase, skills tag cloud, about section, and a Resend-powered contact form. Mobile-first responsive design with strict accessibility and performance requirements. - -## Technical Context - -**Language/Version**: TypeScript 5.x (strict mode) -**Primary Dependencies**: Next.js 14 (App Router), React 18, Tailwind CSS 3.4, Framer Motion 11, React Three Fiber 8, Drei 9, Resend 2.0, Three.js 0.160 -**Storage**: N/A (static content, no database. Resend handles email delivery) -**Testing**: Manual verification against acceptance scenarios (no formal test framework for this portfolio) -**Target Platform**: Web — deployed to Vercel, works on all modern browsers (Chrome, Firefox, Safari, Edge) -**Project Type**: Web application (Next.js full-stack with API route) -**Performance Goals**: LCP <3s on 4G, ≥90 Lighthouse scores, 60fps animations, ≥30fps 3D scene -**Constraints**: No stock photos, no AI brain graphics, no progress bars, reduced motion support, WCAG AA -**Scale/Scope**: Single-page portfolio with 6 sections, 4 project cards, ~20 skill tags, 1 API route - -## Constitution Check - -| Principle | Status | Notes | -|-----------|--------|-------| -| Clarity Over Cleverness | ✅ Pass | Straightforward component architecture, no unnecessary abstractions | -| Mobile-First | ✅ Pass | Tailwind mobile-first breakpoints, responsive grid | -| Performance as Feature | ✅ Pass | Lazy-loaded 3D, optimized images, no render-blocking resources | -| Accessibility | ✅ Pass | Semantic HTML, ARIA labels, keyboard nav, reduced motion | -| No Secrets in Code | ✅ Pass | RESEND_API_KEY in .env, .env.example provided | -| Smallest Viable Change | ✅ Pass | Tasks are incremental and independently testable | - -## Project Structure - -### Documentation (this feature) - -```text -specs/portfolio-website/ -├── spec.md # Feature specification (user stories, requirements) -├── plan.md # This file (architecture and technical decisions) -└── tasks.md # Actionable task list (/sp.tasks output) -``` - -### Source Code (repository root) - -```text -portfolio/ -├── app/ -│ ├── layout.tsx # Root layout (fonts, metadata, global styles) -│ ├── page.tsx # Main page (composes all sections) -│ ├── globals.css # Global CSS (Tailwind imports, CSS variables) -│ └── api/ -│ └── contact/ -│ └── route.ts # Resend contact form API route -├── components/ -│ ├── intro/ -│ │ └── IntroSequence.tsx # Text-slam intro animation -│ ├── hero/ -│ │ ├── Hero.tsx # Hero section (name, title, CTAs) -│ │ └── Scene3D.tsx # React Three Fiber 3D scene -│ ├── projects/ -│ │ ├── Projects.tsx # Projects section container -│ │ └── ProjectCard.tsx # Individual project card -│ ├── skills/ -│ │ └── Skills.tsx # Skills tag cloud section -│ ├── about/ -│ │ └── About.tsx # About section with bio -│ ├── contact/ -│ │ └── ContactForm.tsx # Contact form with Resend integration -│ └── ui/ -│ └── SectionHeading.tsx # Reusable section heading component -├── data/ -│ ├── projects.ts # Project data (4 projects) -│ ├── skills.ts # Skills data (by category) -│ └── socials.ts # Social links data -├── lib/ -│ └── resend.ts # Resend client configuration -├── public/ -│ └── avatar-placeholder.mp4 # Placeholder for HeyGen avatar video -├── .env.example # Environment variable template -├── next.config.js # Next.js configuration -├── tailwind.config.ts # Tailwind configuration (custom colors) -├── tsconfig.json # TypeScript configuration -└── package.json # Dependencies -``` - -**Structure Decision**: Single Next.js web application using App Router. Components organized by section/feature. Data separated into `data/` directory for easy content updates. API route for contact form in `app/api/contact/`. No backend server needed — Resend handles email via API. - -## Key Decisions & Rationale - -### 1. Next.js App Router over Pages Router -**Decision**: Use App Router (Next.js 14) -**Rationale**: App Router is the future of Next.js. Server Components by default reduce client JS. Simpler data fetching patterns. Better streaming support. -**Trade-off**: Slightly newer patterns, but well-documented. - -### 2. React Three Fiber for 3D (Lazy Loaded) -**Decision**: Use RTF + Drei, dynamically imported with `next/dynamic` and `ssr: false` -**Rationale**: RTF is the standard React wrapper for Three.js. Drei provides useful abstractions (Float, OrbitControls). Lazy loading prevents blocking initial render. -**Trade-off**: 3D adds bundle size, but lazy loading mitigates this. Fallback for no-WebGL. - -### 3. Framer Motion for Animations -**Decision**: Framer Motion for all UI animations (intro sequence, scroll transitions) -**Rationale**: Declarative API, excellent React integration, built-in `useReducedMotion()` hook, layout animations, AnimatePresence for exit animations. -**Trade-off**: Adds ~30kb to bundle, but worth it for animation quality and DX. - -### 4. Resend for Contact Form -**Decision**: Resend API with Next.js API route -**Rationale**: Simple API, generous free tier (3000 emails/month), React Email support if needed later, well-documented. -**Trade-off**: Requires API key, but that's standard for email services. - -### 5. Data in Static Files vs Database -**Decision**: Static TypeScript data files (`data/` directory) -**Rationale**: Portfolio content changes infrequently. No need for a database. Static files are simpler, faster, and free. -**Trade-off**: Requires code change to update content, but that's acceptable for a portfolio. - -### 6. No CSS-in-JS (Tailwind Only) -**Decision**: Tailwind CSS utility classes only, no styled-components or emotion -**Rationale**: Tailwind is already in the stack. Zero runtime CSS-in-JS overhead. Smaller bundle. Consistent design tokens. -**Trade-off**: Some verbosity in className strings, but Tailwind's design system enforces consistency. - -## Interfaces & API Contracts - -### Contact Form API - -**Endpoint**: `POST /api/contact` - -**Request Body**: -```json -{ - "name": "string (required, 1-100 chars)", - "email": "string (required, valid email)", - "message": "string (required, 1-2000 chars)" -} -``` - -**Success Response** (200): -```json -{ - "success": true, - "message": "Message sent successfully" -} -``` - -**Error Responses**: -- `400` — Validation error (missing/invalid fields) -- `500` — Server error (Resend failure, missing API key) - -**Validation Rules**: -- `name`: Required, 1-100 characters -- `email`: Required, valid email format -- `message`: Required, 1-2000 characters - -## Non-Functional Requirements - -### Performance -- LCP <3s on 4G -- Lazy load 3D scene (dynamic import, ssr: false) -- Optimize all images (next/image) -- No render-blocking JS in critical path -- Target ≥90 Lighthouse Performance score - -### Reliability -- Contact form handles API errors gracefully -- 3D scene has fallback for no-WebGL -- Form preserves data on error -- Form prevents double-submission - -### Security -- RESEND_API_KEY in environment variable (never in code) -- Input validation server-side -- No XSS vectors (React escapes by default) -- Rate limiting: Client-side debounce + server-side consideration - -### Accessibility -- Semantic HTML (section, nav, main, form, label) -- ARIA labels on interactive elements -- Keyboard navigable -- Color contrast ≥ WCAG AA -- `prefers-reduced-motion` respected everywhere - -## Data Management - -### Source of Truth -- Project data: `data/projects.ts` -- Skills data: `data/skills.ts` -- Social links: `data/socials.ts` - -### Schema Evolution -Data is static TypeScript — no migration needed. Content updates are direct file edits. - -## Operational Readiness - -### Deployment -- Vercel (Next.js native hosting) -- Environment variables configured in Vercel dashboard -- Automatic deployments on push to main - -### Monitoring -- Vercel Analytics (optional, can be added later) -- Resend dashboard for email delivery tracking - -### Rollback -- Git-based — revert to previous commit, Vercel auto-deploys - -## Risk Analysis - -| Risk | Likelihood | Impact | Mitigation | -|------|-----------|--------|------------| -| 3D scene performance on low-end devices | Medium | Medium | Lazy load, fallback for no-WebGL, reduced motion disables 3D | -| Resend API key expiry/rotation | Low | High | Document key rotation in README, monitor Resend dashboard | -| Avatar video placeholder looks unprofessional | Medium | Low | Use a clean placeholder (colored div with initials), replace with HeyGen later | -| Intro sequence annoying on repeat visits | Medium | Low | Use sessionStorage to skip intro on return visits | - -## Complexity Tracking - -No constitution violations. All choices align with the principles. diff --git a/specs/portfolio-website/spec.md b/specs/portfolio-website/spec.md deleted file mode 100644 index 8ee69f5..0000000 --- a/specs/portfolio-website/spec.md +++ /dev/null @@ -1,138 +0,0 @@ -# Feature Specification: Anus Yousuf Portfolio Website - -**Feature Branch**: `001-portfolio-website` -**Created**: 2026-06-23 -**Status**: Draft -**Input**: User description: "Build a personal portfolio website for Anus Yousuf — AI Agent & RAG Chatbot Developer from Karachi, Pakistan. Next.js 14, TypeScript, Tailwind CSS, Framer Motion, React Three Fiber. Dark theme (#0a0a0a bg, white text, orange accent). Intro text-slam sequence, 3D scene, hero, projects, skills, about, contact form with Resend." - -## User Scenarios & Testing *(mandatory)* - -### User Story 1 — First Impression & Hero (Priority: P1) - -A visitor lands on the portfolio and immediately understands who Anus is and what he does. The intro sequence plays, the hero section is clear, and CTAs guide them to explore or get in touch. - -**Why this priority**: This is the entry point. Without it, no other section matters — if the first impression fails, the user leaves. - -**Independent Test**: Load the page in a browser. Verify the intro text-slam sequence plays, the hero shows name + title + two CTAs, and scrolling past the hero transitions smoothly into content. - -**Acceptance Scenarios**: - -1. **Given** the page is loading for the first time, **When** the user visits the site, **Then** a full-screen intro sequence plays with text slam animations ("Still doing it manually?" → "There's an agent for that." → avatar placeholder → "I build them. Scroll down.") -2. **Given** the intro sequence is playing, **When** the user scrolls, **Then** the intro exits and the portfolio sections become visible -3. **Given** the hero section is visible, **When** the user views it, **Then** they see "Anus Yousuf" as the name, "AI Agent & RAG Chatbot Developer" as the title, and two CTAs: "See My Work" and "Contact Me" -4. **Given** the user prefers reduced motion, **When** the page loads, **Then** the intro sequence is skipped and the hero is shown immediately -5. **Given** the user is on mobile, **When** they view the hero, **Then** all elements are readable and properly spaced - ---- - -### User Story 2 — Projects Showcase (Priority: P1) - -A visitor can browse Anus's projects with clear descriptions, tech stacks, and GitHub links. Each project card is informative and visually distinct. - -**Why this priority**: Projects are the core proof of skill. Recruiters and clients want to see what you've built. - -**Independent Test**: Navigate to the Projects section. Verify all 4 project cards render with title, description, tech stack tags, and GitHub links. - -**Acceptance Scenarios**: - -1. **Given** the Projects section is visible, **When** the user views it, **Then** they see a 2-column grid of project cards (1 column on mobile) -2. **Given** a project card, **When** the user reads it, **Then** they see the project name, description, and tech stack tags -3. **Given** a project card with a GitHub link, **When** the user clicks the link, **Then** it opens the GitHub repo in a new tab -4. **Given** the user is on mobile, **When** they view the projects, **Then** cards stack in a single column - ---- - -### User Story 3 — Skills & About (Priority: P2) - -A visitor can quickly scan Anus's technical skills organized by category and read a short about section. - -**Why this priority**: Skills provide a quick overview of capabilities. The about section adds personality and context. - -**Independent Test**: Navigate to Skills and About sections. Verify skills are displayed as tag cloud by category (no progress bars), and the about section shows a first-person paragraph. - -**Acceptance Scenarios**: - -1. **Given** the Skills section is visible, **When** the user views it, **Then** they see skill tags organized by category (Languages, Frameworks, AI, Infrastructure) -2. **Given** the Skills section, **When** the user inspects it, **Then** there are NO progress bars or percentage indicators -3. **Given** the About section is visible, **When** the user reads it, **Then** they see a first-person paragraph about Anus -4. **Given** the About section, **When** the user views it, **Then** it includes links to GitHub, LinkedIn, and X (Twitter) - ---- - -### User Story 4 — Contact Form (Priority: P2) - -A visitor can send a message via the contact form. The form validates inputs and sends via Resend API. - -**Why this priority**: The contact form is the conversion point — it's how opportunities come in. - -**Independent Test**: Fill out and submit the contact form. Verify the message is sent via Resend and the user gets success/error feedback. - -**Acceptance Scenarios**: - -1. **Given** the Contact section is visible, **When** the user views it, **Then** they see name, email, and message fields with a submit button -2. **Given** the form is empty, **When** the user clicks submit, **Then** validation errors are shown for required fields -3. **Given** the form has valid data, **When** the user submits, **Then** a loading state is shown and the message is sent via Resend API -4. **Given** the message sends successfully, **When** the API responds, **Then** a success message is displayed -5. **Given** the API returns an error, **When** the response arrives, **Then** an error message is displayed and the form data is preserved - ---- - -### User Story 5 — 3D Scene (Priority: P3) - -A visitor sees an interactive 3D scene with floating geometric shapes and orange accent lighting in the hero area. - -**Why this priority**: The 3D scene adds visual polish and differentiation, but the site works without it. - -**Independent Test**: Load the page and verify the 3D scene renders with floating shapes, responds to mouse movement, and dissolves on scroll. - -**Acceptance Scenarios**: - -1. **Given** the hero section is visible, **When** the user views it, **Then** a 3D canvas with floating geometric shapes is rendered -2. **Given** the 3D scene is active, **When** the user moves their mouse, **Then** the scene responds to mouse movement -3. **Given** the 3D scene is active, **When** the user scrolls past the hero, **Then** the 3D scene dissolves/fades out -4. **Given** the user is on a low-power device or WebGL is unavailable, **When** the page loads, **Then** the site still works with a fallback (static or no 3D) - ---- - -### Edge Cases - -- What happens when the Resend API key is not configured? → Show a user-friendly error, log server-side -- What happens on very narrow screens (<320px)? → Content should not overflow, use `min-w-0` and text truncation -- What happens when JavaScript is disabled? → Core content (hero text, projects, skills, about) should still be visible; 3D scene and animations gracefully degrade -- What happens when the avatar video fails to load? → Show a placeholder (static image or colored div with initials) -- What happens when the user submits the form multiple times rapidly? → Disable submit button during submission to prevent duplicates - -## Requirements *(mandatory)* - -### Functional Requirements - -- **FR-001**: System MUST display an intro text-slam animation sequence on first load that exits on scroll -- **FR-002**: System MUST display a hero section with name, title, and two CTAs ("See My Work" anchors to Projects, "Contact Me" anchors to Contact) -- **FR-003**: System MUST display 4 project cards in a responsive 2-column grid with title, description, tech stack tags, and GitHub links -- **FR-004**: System MUST display skills as a tag cloud organized by category with NO progress bars -- **FR-005**: System MUST display an About section with first-person bio and social links -- **FR-006**: System MUST provide a contact form with name, email, and message fields that submits via Resend API -- **FR-007**: System MUST render an interactive 3D scene using React Three Fiber that responds to mouse movement and dissolves on scroll -- **FR-008**: System MUST respect `prefers-reduced-motion` — skip intro animation, reduce/remove 3D motion -- **FR-009**: System MUST be fully responsive (mobile, tablet, desktop) -- **FR-010**: System MUST use the specified color palette (#0a0a0a background, #ffffff text, #f97316 accent) -- **FR-011**: System MUST lazy-load the 3D scene to avoid blocking initial render -- **FR-012**: System MUST use semantic HTML and meet WCAG AA accessibility standards - -### Key Entities - -- **Project**: name (string), description (string), techStack (string[]), githubUrl (string) -- **SkillCategory**: name (string), skills (string[]) -- **ContactMessage**: name (string), email (string), message (string) -- **SocialLink**: platform (string), url (string), label (string) - -## Success Criteria *(mandatory)* - -### Measurable Outcomes - -- **SC-001**: Page loads with Largest Contentful Paint (LCP) under 3 seconds on 4G connection -- **SC-002**: All sections are visible and functional on viewports from 320px to 2560px wide -- **SC-003**: Contact form successfully sends messages via Resend API with <2s response time -- **SC-004**: Site scores ≥90 on Lighthouse Performance, Accessibility, and Best Practices -- **SC-005**: Intro sequence plays smoothly at 60fps on mid-range devices -- **SC-006**: 3D scene renders at ≥30fps on devices with WebGL support diff --git a/specs/portfolio-website/tasks.md b/specs/portfolio-website/tasks.md deleted file mode 100644 index 6f14de7..0000000 --- a/specs/portfolio-website/tasks.md +++ /dev/null @@ -1,178 +0,0 @@ -# Tasks: Anus Yousuf Portfolio Website - -**Input**: Design documents from `/specs/portfolio-website/` -**Prerequisites**: plan.md ✅, spec.md ✅ - -**Organization**: Tasks are grouped by user story to enable independent implementation and testing of each story. - -## Format: `[ID] [P?] [Story] Description` - -- **[P]**: Can run in parallel (different files, no dependencies) -- **[Story]**: Which user story this task belongs to (e.g., US1, US2, US3) - ---- - -## Phase 1: Setup (Shared Infrastructure) - -**Purpose**: Project initialization and basic structure - -- [ ] T001 Initialize Next.js 14 project with TypeScript and Tailwind CSS -- [ ] T002 [P] Configure Tailwind with custom colors (#0a0a0a, #ffffff, #f97316) in tailwind.config.ts -- [ ] T003 [P] Create .env.example with RESEND_API_KEY placeholder -- [ ] T004 [P] Create project directory structure (components/, data/, lib/, app/api/) -- [ ] T005 Install dependencies: framer-motion, @react-three/fiber, @react-three/drei, three, resend - ---- - -## Phase 2: Foundational (Blocking Prerequisites) - -**Purpose**: Core infrastructure that MUST be complete before ANY user story can be implemented - -- [ ] T006 Create app/globals.css with Tailwind imports and CSS variables for colors -- [ ] T007 Create app/layout.tsx with metadata, font imports, and global structure -- [ ] T008 Create data/projects.ts with 4 project entries (Commit Voice, Nestaro Pilot, Sparkflow Lead Agent, RAG Chatbot) -- [ ] T009 [P] Create data/skills.ts with skills organized by category (Languages, Frameworks, AI, Infrastructure) -- [ ] T010 [P] Create data/socials.ts with GitHub, LinkedIn, X links -- [ ] T011 Create lib/resend.ts with Resend client initialization -- [ ] T012 Create app/api/contact/route.ts with POST handler (validation + Resend send) -- [ ] T013 Create components/ui/SectionHeading.tsx reusable heading component - -**Checkpoint**: Foundation ready — user story implementation can now begin - ---- - -## Phase 3: User Story 1 — First Impression & Hero (Priority: P1) 🎯 MVP - -**Goal**: Intro sequence plays on first load, hero section displays name/title/CTAs, scroll transitions work - -**Independent Test**: Load page → intro plays → scroll → hero visible with name, title, two CTAs - -- [ ] T014 [P] [US1] Create components/intro/IntroSequence.tsx — text slam animation with Framer Motion ("Still doing it manually?" → "There's an agent for that." → avatar placeholder → "I build them. Scroll down."), exits on scroll, respects prefers-reduced-motion -- [ ] T015 [P] [US1] Create components/hero/Hero.tsx — name "Anus Yousuf", title "AI Agent & RAG Chatbot Developer", two CTAs ("See My Work" → #projects, "Contact Me" → #contact) -- [ ] T016 [P] [US1] Create components/hero/Scene3D.tsx — React Three Fiber canvas with floating geometric shapes, orange accent lighting, ambient rotation, mouse movement response (dynamically imported, ssr: false) -- [ ] T017 [US1] Compose hero section integrating Hero.tsx and Scene3D.tsx with proper layout (3D as background, text overlay) -- [ ] T018 [US1] Wire up scroll-based transition: intro exits → hero + 3D scene visible → scroll past hero → 3D dissolves -- [ ] T019 [US1] Add sessionStorage logic to skip intro on return visits - -**Checkpoint**: US1 complete — intro and hero work independently - ---- - -## Phase 4: User Story 2 — Projects Showcase (Priority: P1) 🎯 MVP - -**Goal**: 4 project cards in responsive 2-column grid with descriptions, tags, GitHub links - -**Independent Test**: Navigate to #projects → see 4 cards with title, description, tech tags, GitHub links - -- [ ] T020 [P] [US2] Create components/projects/ProjectCard.tsx — card with project name, description, tech stack tags, GitHub link (opens in new tab) -- [ ] T021 [US2] Create components/projects/Projects.tsx — section container with 2-column grid (1-col on mobile), maps data/projects.ts through ProjectCard -- [ ] T022 [US2] Add scroll-triggered entrance animation to project cards (staggered fade-in) - -**Checkpoint**: US2 complete — projects section works independently - ---- - -## Phase 5: User Story 3 — Skills & About (Priority: P2) - -**Goal**: Skills tag cloud by category, about section with bio and social links - -**Independent Test**: Navigate to #skills → see tag cloud by category. Navigate to #about → see bio paragraph + social links. - -- [ ] T023 [P] [US3] Create components/skills/Skills.tsx — tag cloud layout, skills grouped by category, NO progress bars, tags styled with subtle borders/background -- [ ] T024 [P] [US3] Create components/about/About.tsx — first-person bio paragraph, social links (GitHub, LinkedIn, X) with icons -- [ ] T025 [US3] Add scroll-triggered entrance animation to skills and about sections - -**Checkpoint**: US3 complete — skills and about sections work independently - ---- - -## Phase 6: User Story 4 — Contact Form (Priority: P2) - -**Goal**: Working contact form with validation, Resend integration, success/error states - -**Independent Test**: Fill form → submit → message sent via Resend → success message shown - -- [ ] T026 [US4] Create components/contact/ContactForm.tsx — name, email, message fields with labels, client-side validation, loading state, success/error feedback -- [ ] T027 [US4] Implement form submission handler (fetch POST to /api/contact) -- [ ] T028 [US4] Add double-submission prevention (disable button during submit) -- [ ] T029 [US4] Wire up API route validation: return 400 for missing/invalid fields, 500 for server errors - -**Checkpoint**: US4 complete — contact form works end-to-end - ---- - -## Phase 7: User Story 5 — 3D Scene Polish (Priority: P3) - -**Goal**: 3D scene is polished with proper lighting, smooth interaction, and graceful fallback - -**Independent Test**: 3D scene renders at ≥30fps, responds to mouse, dissolves on scroll, fallback works without WebGL - -- [ ] T030 [US5] Polish Scene3D.tsx: add proper ambient + point lighting (orange accent), smooth mouse-follow with lerp -- [ ] T031 [US5] Add dissolve/fade-out animation when scrolling past hero (opacity transition via Framer Motion) -- [ ] T032 [US5] Add WebGL detection fallback — show static gradient background if WebGL unavailable -- [ ] T033 [US5] Ensure 3D scene is dynamically imported with ssr: false to avoid SSR issues - -**Checkpoint**: US5 complete — 3D scene is polished and resilient - ---- - -## Phase 8: Polish & Cross-Cutting Concerns - -**Purpose**: Final improvements across all sections - -- [ ] T034 [P] Compose app/page.tsx — assemble all sections in order: IntroSequence, Hero (with Scene3D), Projects, Skills, About, ContactForm -- [ ] T035 [P] Add smooth scroll behavior and section anchor links -- [ ] T036 [P] Add scroll-triggered section entrance animations (fade/slide up) -- [ ] T037 Verify responsive design: test at 320px, 768px, 1024px, 1440px, 2560px -- [ ] T038 Verify prefers-reduced-motion: skip intro, reduce animations, disable 3D motion -- [ ] T039 Verify accessibility: semantic HTML, ARIA labels, keyboard navigation, color contrast -- [ ] T040 Run Lighthouse audit and address any issues below 90 score -- [ ] T041 Add loading states and error boundaries where applicable - ---- - -## Dependencies & Execution Order - -### Phase Dependencies - -- **Setup (Phase 1)**: No dependencies — start immediately -- **Foundational (Phase 2)**: Depends on Setup — BLOCKS all user stories -- **User Stories (Phase 3-7)**: All depend on Foundational completion - - US1 and US2 can proceed in parallel (P1 priority) - - US3, US4, US5 can proceed in parallel after Foundational -- **Polish (Phase 8)**: Depends on all user stories being complete - -### User Story Dependencies - -- **US1 (P1)**: After Foundational — No story dependencies -- **US2 (P1)**: After Foundational — No story dependencies -- **US3 (P2)**: After Foundational — No story dependencies -- **US4 (P2)**: After Foundational — Depends on T012 (API route) from Foundational -- **US5 (P3)**: After Foundational — Enhances T016 from US1 - -### Parallel Opportunities - -- All Setup tasks marked [P] can run in parallel -- All Foundational tasks marked [P] can run in parallel -- US1 and US2 can be worked on simultaneously after Foundational -- US3, US4, US5 can run in parallel after Foundational - ---- - -## Implementation Strategy - -### MVP First (US1 + US2) - -1. Complete Phase 1: Setup -2. Complete Phase 2: Foundational -3. Complete Phase 3: US1 (Intro + Hero) -4. Complete Phase 4: US2 (Projects) -5. **STOP and VALIDATE**: Test intro → hero → projects flow -6. Deploy to Vercel for early feedback - -### Incremental Delivery - -1. Add US3 → Skills + About → Validate -2. Add US4 → Contact Form → Validate -3. Add US5 → 3D Polish → Validate -4. Polish phase → Final validation → Launch