chore: update speckit tooling, Claude commands, and agent instructions

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Author: InfantLab

.claude/commands/speckit-clarify.md

@@ -0,0 +1,56 @@
+Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
+
+## 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.
+
+This clarification workflow runs BEFORE `/speckit-plan`. If the user explicitly states they are skipping clarification, warn that downstream rework risk increases.
+
+1. Run the prerequisites script from repo root once:
+   ```bash
+   bash .specify/scripts/bash/check-prerequisites.sh --json --paths-only
+   ```
+   Parse: `FEATURE_DIR`, `FEATURE_SPEC`. If JSON parsing fails, abort and instruct user to re-run `/speckit-specify`.
+
+2. Load the current spec file. Perform a structured ambiguity & coverage scan using this taxonomy (mark each: Clear / Partial / Missing):
+
+   - Functional Scope & Behavior (core goals, out-of-scope, user roles)
+   - Domain & Data Model (entities, attributes, relationships, lifecycle, scale)
+   - Interaction & UX Flow (critical journeys, error/empty/loading states, accessibility)
+   - Non-Functional Quality Attributes (performance, scalability, reliability, observability, security, compliance)
+   - Integration & External Dependencies (services/APIs, failure modes, formats)
+   - Edge Cases & Failure Handling (negative scenarios, rate limiting, conflicts)
+   - Constraints & Tradeoffs (technical constraints, rejected alternatives)
+   - Terminology & Consistency (canonical terms, avoided synonyms)
+   - Completion Signals (acceptance criteria testability, Definition of Done)
+   - Misc / Placeholders (TODOs, vague adjectives lacking quantification)
+
+3. Generate a prioritized queue of max 5 clarification questions. Each must be answerable with multiple-choice (2-5 options) or short answer (<=5 words). Only include questions whose answers materially impact architecture, data modeling, task decomposition, test design, UX, operational readiness, or compliance.
+
+4. **Sequential questioning** — present ONE question at a time:
+   - For multiple-choice: Present **Recommended** option prominently with reasoning, then all options as a table. User can reply with letter, "yes"/"recommended", or own answer.
+   - For short-answer: Present **Suggested** answer with reasoning. User can accept or provide own.
+   - Stop when: all critical ambiguities resolved, user signals "done", or 5 questions asked.
+
+5. **After EACH accepted answer**, update the spec:
+   - Ensure `## Clarifications` section exists (create after overview if missing)
+   - Add `### Session YYYY-MM-DD` subheading
+   - Append bullet: `- Q: <question> → A: <answer>`
+   - Apply clarification to the appropriate spec section(s)
+   - Save the spec file after each integration
+
+6. Validate after each write: no duplicates, no contradictions, no lingering placeholders, consistent terminology.
+
+7. Report completion: questions asked/answered, path to updated spec, sections touched, coverage summary table (Resolved/Deferred/Clear/Outstanding), suggested next command.
+
+If no meaningful ambiguities found, respond: "No critical ambiguities detected" and suggest proceeding to `/speckit-plan`.
+
+Context for prioritization: $ARGUMENTS

.claude/commands/speckit-implement.md

@@ -0,0 +1,44 @@
+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).
+
+## Pre-Execution Checks
+
+Check if `.specify/extensions.yml` exists. If so, check `hooks.before_implement` for enabled hooks. Execute mandatory hooks; display optional hooks.
+
+## Outline
+
+1. **Setup**: Run from repo root:
+   ```bash
+   bash .specify/scripts/bash/check-prerequisites.sh --json --require-tasks --include-tasks
+   ```
+   Parse FEATURE_DIR and AVAILABLE_DOCS.
+
+2. **Check checklists** (if FEATURE_DIR/checklists/ exists):
+   - Count total/completed/incomplete items per checklist
+   - If incomplete: STOP and ask user to proceed or halt
+   - If all complete: proceed automatically
+
+3. **Load context**: tasks.md (required), plan.md (required), plus data-model.md, contracts/, research.md, quickstart.md if they exist.
+
+4. **Project setup verification**: Create/verify ignore files (.gitignore, .dockerignore, etc.) based on detected tech stack.
+
+5. **Parse tasks.md**: Extract phases, dependencies, parallel markers.
+
+6. **Execute phase-by-phase**:
+   - Complete each phase before moving to next
+   - Respect sequential dependencies; run parallel [P] tasks together
+   - Follow TDD if tests exist
+   - Mark completed tasks as `[X]` in tasks.md
+
+7. **Progress tracking**: Report after each task. Halt on non-parallel failures. Clear error messages.
+
+8. **Completion validation**: Verify all tasks done, features match spec, tests pass.
+
+9. Check `hooks.after_implement` if extensions.yml exists.

.claude/commands/speckit-plan.md

@@ -0,0 +1,51 @@
+Execute the implementation planning workflow to generate design artifacts.
+
+## User Input
+
+```text
+$ARGUMENTS
+```
+
+You **MUST** consider the user input before proceeding (if not empty).
+
+## Outline
+
+1. **Setup**: Run from repo root and parse JSON:
+   ```bash
+   bash .specify/scripts/bash/setup-plan.sh --json
+   ```
+   Extract: FEATURE_SPEC, IMPL_PLAN, SPECS_DIR, BRANCH.
+
+2. **Load context**: Read FEATURE_SPEC and `.specify/memory/constitution.md`. Load IMPL_PLAN template.
+
+3. **Execute plan workflow** following the IMPL_PLAN template:
+   - Fill Technical Context (mark unknowns as "NEEDS CLARIFICATION")
+   - Fill Constitution Check section
+   - 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:
+     ```bash
+     bash .specify/scripts/bash/update-agent-context.sh __AGENT__
+     ```
+   - Re-evaluate Constitution Check post-design
+
+4. **Stop and report**: Command ends after Phase 1. Report branch, IMPL_PLAN path, and generated artifacts.
+
+### Phase 0: Outline & Research
+
+- Extract unknowns from Technical Context → research tasks
+- For each dependency → best practices task
+- Consolidate findings in `research.md` (Decision, Rationale, Alternatives)
+
+### Phase 1: Design & Contracts
+
+- Extract entities from spec → `data-model.md`
+- Define interface contracts (if applicable) → `/contracts/`
+- Generate `quickstart.md`
+- Run agent context update script
+
+## Key rules
+
+- Use absolute paths
+- ERROR on gate failures or unresolved clarifications

.claude/commands/speckit-specify.md

@@ -0,0 +1,34 @@
+Create or update the feature specification from a natural language feature description.
+
+## User Input
+
+```text
+$ARGUMENTS
+```
+
+You **MUST** consider the user input before proceeding (if not empty).
+
+## Outline
+
+The text the user typed after the command **is** the feature description.
+
+Given that feature description:
+
+1. **Generate a concise short name** (2-4 words) for the branch in action-noun format.
+
+2. **Create the feature branch** (do NOT pass `--number` — auto-detected):
+   ```bash
+   bash .specify/scripts/bash/create-new-feature.sh --json --short-name "short-name" "Feature description"
+   ```
+
+3. Load `.specify/templates/spec-template.md` for required sections.
+
+4. Parse description, extract actors/actions/data/constraints. Make informed guesses for unclear aspects. Mark max 3 items with `[NEEDS CLARIFICATION]` only if the choice significantly impacts scope, has multiple reasonable interpretations, and no reasonable default exists.
+
+5. Write the spec to SPEC_FILE using the template. Focus on **WHAT** and **WHY**, not HOW. Written for business stakeholders.
+
+6. **Validate** against quality criteria. Create checklist at `FEATURE_DIR/checklists/requirements.md`. If items fail, fix and re-validate (max 3 iterations). If clarifications remain (max 3), present questions with options.
+
+7. Report completion with branch name, spec file path, checklist results, and next step (`/speckit-clarify` or `/speckit-plan`).
+
+**NOTE:** The script creates and checks out the new branch and initializes the spec file before writing.

.claude/commands/speckit-tasks.md

@@ -0,0 +1,50 @@
+Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.
+
+## User Input
+
+```text
+$ARGUMENTS
+```
+
+You **MUST** consider the user input before proceeding (if not empty).
+
+## Pre-Execution Checks
+
+Check if `.specify/extensions.yml` exists. If so, check `hooks.before_tasks` for enabled hooks. Execute mandatory hooks before proceeding; display optional hooks.
+
+## Outline
+
+1. **Setup**: Run from repo root:
+   ```bash
+   bash .specify/scripts/bash/check-prerequisites.sh --json
+   ```
+   Parse FEATURE_DIR and AVAILABLE_DOCS.
+
+2. **Load design documents** from FEATURE_DIR:
+   - **Required**: plan.md, spec.md
+   - **Optional**: data-model.md, contracts/, research.md, quickstart.md
+
+3. **Generate tasks** organized by user story:
+   - Extract tech stack and user stories with priorities
+   - Map entities and contracts to stories
+   - Generate dependency graph and parallel execution examples
+
+4. **Write tasks.md** using `.specify/templates/tasks-template.md`:
+   - Phase 1: Setup (project init)
+   - Phase 2: Foundational (blocking prerequisites)
+   - Phase 3+: One phase per user story (priority order)
+   - Final: Polish & cross-cutting
+
+5. **Task format** (REQUIRED):
+   ```
+   - [ ] [TaskID] [P?] [Story?] Description with file path
+   ```
+   - Checkbox always starts with `- [ ]`
+   - Sequential ID: T001, T002...
+   - `[P]` only if parallelizable
+   - `[US1]`, `[US2]` etc. for user story phases only
+   - Clear file path in description
+
+6. **Report**: Path, total count, per-story count, parallel opportunities, MVP scope.
+
+7. Check `hooks.after_tasks` if extensions.yml exists.

.claude/settings.json

@@ -38,11 +38,43 @@
       "Bash(npm ls:*)",
       "Bash(npx tsc:*)",
       "Bash(npx vue-tsc:*)",
-      "Bash(echo $?)"
+      "Bash(echo $?)",
+      "Bash(bunx eslint:*)",
+      "Bash(then echo:*)",
+      "Bash(DATABASE_URL=file:../data/db.sqlite timeout 90 bun vitest --run --reporter=verbose)",
+      "Bash(DATABASE_URL=file:../data/db.sqlite bun vitest --run)",
+      "Bash(npm run:*)",
+      "Bash(DATABASE_URL=file:../data/db.sqlite timeout 180 bun vitest --run --reporter=verbose)",
+      "Bash(npx eslint:*)",
+      "Bash(node_modules/.bin/eslint tests/server/api/admin.test.ts tests/server/api/auth.test.ts tests/server/api/entries.test.ts tests/server/services/stripe.test.ts tests/server/services/syncEngine.test.ts registry/entryTypes.test.ts)",
+      "Bash(node_modules/.bin/nuxi typecheck:*)",
+      "Bash(while read:*)",
+      "Bash(do sed:*)",
+      "Bash(done)",
+      "Bash(git tag -a v0.5.0 -m \"v0.5.0: Housekeeping & Infrastructure:*)",
+      "WebFetch(domain:docs.docker.com)",
+      "WebFetch(domain:releasebot.io)",
+      "Bash(wsl --version)",
+      "Bash(wsl --status)",
+      "Read(//c/Users/caspar/code/tada/$USERPROFILE/**)",
+      "Read(//c/Users/caspar/code/tada/$APPDATA/Docker/**)",
+      "Bash(powershell.exe -Command \"Get-ComputerInfo | Select-Object WindowsProductName, WindowsVersion, OsBuildNumber, OsHardwareAbstractionLayer, CsModel, CsManufacturer | Format-List\")",
+      "Bash(python -m json.tool)",
+      "Bash(powershell.exe -Command \"Get-WinEvent -FilterHashtable @{LogName=''System''; ProviderName=''Microsoft-Windows-Kernel-Power''; Id=107,507} -MaxEvents 10 2>&1 | Format-Table TimeCreated, Id, Message -Wrap\")",
+      "Bash(bunx @spec-kit/cli@latest)",
+      "Bash(cp -r /tmp/spec-kit-latest/templates/* /workspaces/tada/.specify/templates/)",
+      "Bash(cp -r /tmp/spec-kit-latest/scripts/* /workspaces/tada/.specify/scripts/)",
+      "Bash(bash .specify/scripts/bash/create-new-feature.sh --json --short-name \"weekly-rhythms\" \"Weekly Rhythms — Encouragement & Celebration: Thursday mid-week nudge and Sunday end-of-week celebration summary with tiered AI options\")",
+      "Bash(bash .specify/scripts/bash/check-prerequisites.sh --json --require-tasks --include-tasks)",
+      "Bash(DATABASE_URL=file:../data/db.sqlite drizzle-kit push)",
+      "Bash(DATABASE_URL=file:../data/db.sqlite bun drizzle-kit push --config=drizzle.config.ts)"
     ],
     "additionalDirectories": [
       "/tmp",
-      "/workspaces/tada/specs"
+      "/workspaces/tada/specs",
+      "C:\\Users\\caspar\\scripts",
+      "/workspaces/tada/.claude",
+      "/workspaces/tada/app/server/api/weekly-rhythms/messages"
     ]
   }
 }

.github/agents/copilot-instructions.md

@@ -1,6 +1,6 @@
 # tada Development Guidelines
 
-Auto-generated from all feature plans. Last updated: 2026-01-14
+Auto-generated from all feature plans. Last updated: 2026-03-18
 
 ## Active Technologies
 - TypeScript 5.x, Vue 3.4+, Nuxt 3.x + Drizzle ORM, TailwindCSS, Lucia Auth (002-graceful-rhythms)
@@ -9,6 +9,8 @@ Auto-generated from all feature plans. Last updated: 2026-01-14
 - SQLite (Drizzle), IndexedDB (audio blobs, model cache) (003-voice-input-llm)
 - TypeScript 5.x, Vue 3.4+, Nuxt 3.x + Nuxt 3, Vue 3, Drizzle ORM, SQLite, Zod (validation) (004-better-add)
 - SQLite via Drizzle ORM (`app/server/db/schema.ts`) (004-better-add)
+- TypeScript 5.9, Vue 3, Nuxt 4 + Drizzle ORM, Zod, Nodemailer, existing rhythm calculators, existing email templates, provider adapter for cloud AI, direct `croner` dependency during implementation for scheduler sweeps (009-weekly-rhythms)
+- SQLite via Drizzle, plus existing environment-variable based SMTP/AI credentials (009-weekly-rhythms)
 
 - TypeScript 5.x (strict mode), Vue 3 Composition API + Nuxt 3, Drizzle ORM, TailwindCSS (001-v020-completion)
 
@@ -28,9 +30,9 @@ npm test && npm run lint
 TypeScript 5.x (strict mode), Vue 3 Composition API: Follow standard conventions
 
 ## Recent Changes
+- 009-weekly-rhythms: Added TypeScript 5.9, Vue 3, Nuxt 4 + Drizzle ORM, Zod, Nodemailer, existing rhythm calculators, existing email templates, provider adapter for cloud AI, direct `croner` dependency during implementation for scheduler sweeps
 - 004-better-add: Added [if applicable, e.g., PostgreSQL, CoreData, files or N/A]
 - 004-better-add: Added TypeScript 5.x, Vue 3.4+, Nuxt 3.x + Nuxt 3, Vue 3, Drizzle ORM, SQLite, Zod (validation)
-- 003-voice-input-llm: Added TypeScript 5.x, Node.js 20 (production), Bun (development) + Nuxt 3, Vue 3, Drizzle ORM, Whisper.cpp (WASM), WebLLM
 
 
 <!-- MANUAL ADDITIONS START -->

.specify/scripts/bash/check-prerequisites.sh

@@ -79,15 +79,28 @@ SCRIPT_DIR="$(CDPATH="" cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 source "$SCRIPT_DIR/common.sh"
 
 # Get feature paths and validate branch
-eval $(get_feature_paths)
+_paths_output=$(get_feature_paths) || { echo "ERROR: Failed to resolve feature paths" >&2; exit 1; }
+eval "$_paths_output"
+unset _paths_output
 check_feature_branch "$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" "$TASKS"
+        if has_jq; then
+            jq -cn \
+                --arg repo_root "$REPO_ROOT" \
+                --arg branch "$CURRENT_BRANCH" \
+                --arg feature_dir "$FEATURE_DIR" \
+                --arg feature_spec "$FEATURE_SPEC" \
+                --arg impl_plan "$IMPL_PLAN" \
+                --arg tasks "$TASKS" \
+                '{REPO_ROOT:$repo_root,BRANCH:$branch,FEATURE_DIR:$feature_dir,FEATURE_SPEC:$feature_spec,IMPL_PLAN:$impl_plan,TASKS:$tasks}'
+        else
+            printf '{"REPO_ROOT":"%s","BRANCH":"%s","FEATURE_DIR":"%s","FEATURE_SPEC":"%s","IMPL_PLAN":"%s","TASKS":"%s"}\n' \
+                "$(json_escape "$REPO_ROOT")" "$(json_escape "$CURRENT_BRANCH")" "$(json_escape "$FEATURE_DIR")" "$(json_escape "$FEATURE_SPEC")" "$(json_escape "$IMPL_PLAN")" "$(json_escape "$TASKS")"
+        fi
     else
         echo "REPO_ROOT: $REPO_ROOT"
         echo "BRANCH: $CURRENT_BRANCH"
@@ -141,14 +154,25 @@ fi
 # Output results
 if $JSON_MODE; then
     # Build JSON array of documents
-    if [[ ${#docs[@]} -eq 0 ]]; then
-        json_docs="[]"
+    if has_jq; then
+        if [[ ${#docs[@]} -eq 0 ]]; then
+            json_docs="[]"
+        else
+            json_docs=$(printf '%s\n' "${docs[@]}" | jq -R . | jq -s .)
+        fi
+        jq -cn \
+            --arg feature_dir "$FEATURE_DIR" \
+            --argjson docs "$json_docs" \
+            '{FEATURE_DIR:$feature_dir,AVAILABLE_DOCS:$docs}'
     else
-        json_docs=$(printf '"%s",' "${docs[@]}")
-        json_docs="[${json_docs%,}]"
+        if [[ ${#docs[@]} -eq 0 ]]; then
+            json_docs="[]"
+        else
+            json_docs=$(for d in "${docs[@]}"; do printf '"%s",' "$(json_escape "$d")"; done)
+            json_docs="[${json_docs%,}]"
+        fi
+        printf '{"FEATURE_DIR":"%s","AVAILABLE_DOCS":%s}\n' "$(json_escape "$FEATURE_DIR")" "$json_docs"
     fi
-    
-    printf '{"FEATURE_DIR":"%s","AVAILABLE_DOCS":%s}\n' "$FEATURE_DIR" "$json_docs"
 else
     # Text output
     echo "FEATURE_DIR:$FEATURE_DIR"