Ellyse/smoketest timing

tools/ralph/Dockerfile

@@ -73,4 +73,4 @@ ENV PATH="/app/labs/tools/ralph/bin:$PATH"
 # If you want to run ralph normally without the smoketest, then replace with:
 # CMD ["/bin/sh", "-c", "/app/start-servers.sh & sleep infinity"]
 # Note: Directories are pre-created by run_smoketest.sh to ensure correct ownership
-CMD ["/bin/sh", "-c", "/app/start-servers.sh & sleep 5 && /app/labs/tools/ralph/bin/ralph-smoketest.sh > /app/smoketest/${RALPH_ID}/ralph.log 2>&1"]
+CMD ["/bin/bash", "-c", "/app/start-servers.sh & sleep 5 && TIMEFORMAT='%R'; { time /app/labs/tools/ralph/bin/ralph-smoketest.sh > /app/smoketest/${RALPH_ID}/ralph.log 2>&1 ; } 2> /app/smoketest/${RALPH_ID}/TIMING_SECONDS.txt"]

tools/ralph/README.md

@@ -37,7 +37,7 @@ variable.
 
 **Option 1: Use the automated script (recommended)**
 
-Run multiple smoketests in parallel (currently configured for tasks 1-8):
+Run multiple smoketests in parallel (currently configured for tasks 1-9):
 
 ```bash
 ./tools/ralph/bin/run_smoketest.sh
@@ -113,6 +113,7 @@ Results are available on the host machine in
 - `ralph.log` - Complete log of Ralph's execution (stdout and stderr)
 - `SCORE.txt` - Contains SUCCESS, PARTIAL, or FAILURE
 - `RESULTS.md` - Summary of work including test results
+- `TIMING_SECONDS.txt` - Total execution time in seconds (decimal format)
 - Pattern files (created directly in this directory for automatic cleanup)
 
 No need to copy files from the container - the bind mount makes results

tools/ralph/SMOKETEST_PROMPT.md

@@ -1,31 +1,25 @@
 # Smoketest Ralph General Prompt
 
-Goal: implement the unchecked item from `./tools/ralph/TASKS.md` that matches
-your assigned RALPH_ID
+Goal: implement the task below
 
-1. Open `/app/labs/tools/ralph/TASKS.md` and find the task numbered with your
-   RALPH_ID.
+<SMOKETEST_TASK>
 
-2. If your assigned task is already checked `[x]`, exit with a message saying
-   the task is already complete.
-
-3. Use Claude Skills "pattern-dev" to work on the task that corresponds to your
-   RALPH_ID number.
+1. Use Claude Skills "pattern-dev" to work on the task above.
 
    IMPORTANT:
    - Create your pattern files directly in /app/smoketest/${RALPH_ID}/
    - Use space name "ralph${RALPH_ID}" (e.g., ralph1, ralph2, ralph3) to avoid
      conflicts with other parallel smoketests
 
-4. Format with `deno fmt` for the changed files.
+2. Format with `deno fmt` for the changed files.
 
-5. Once tests pass, deploy it locally using
+3. Once tests pass, deploy it locally using
    `/app/labs/docs/common/PATTERN_DEV_DEPLOY.md` for info on how to deploy. It
    should deploy to http://localhost:8000. Servers are already running.
 
    Remember to use space name "ralph${RALPH_ID}" when deploying.
 
-6. Once it is deployed locally, test your work using Playwright MCP tools
+4. Once it is deployed locally, test your work using Playwright MCP tools
    directly.
 
    IMPORTANT: Use the MCP tools (like `mcp__playwright__browser_navigate`,
@@ -43,19 +37,19 @@ your assigned RALPH_ID
    - Verify behavior matches task requirements
    - Take final screenshot showing successful interactions
 
-7. Create a summary of your work in /app/smoketest/${RALPH_ID}/RESULTS.md
+5. Create a summary of your work in /app/smoketest/${RALPH_ID}/RESULTS.md
    Include:
    - What pattern you implemented
    - Test results (deno test output)
    - Playwright test results and what you tested
    - Any issues or limitations
 
-8. Create /app/smoketest/${RALPH_ID}/SCORE.txt with one of the following values
+6. Create /app/smoketest/${RALPH_ID}/SCORE.txt with one of the following values
    based on your results:
    - SUCCESS: All tests pass, pattern works as expected
    - PARTIAL: Some tests pass, pattern partially works
    - FAILURE: Tests fail or pattern doesn't work
 
-9. Exit
+7. Exit
 
 Please begin.

tools/ralph/TASKS.md

@@ -5,7 +5,13 @@
    - Data: Current count value
    - Features: Increment, decrement, reset to zero
 
-2. [ ] Shopping List with sort-by-category and budget tracking. These should be
+2. [ ] Dice Roller
+   - Components: Roll button + Result display showing dice emoji and number
+   - Data: Current dice value (1-6)
+   - Features: Click button to roll dice, display random result (1-6) with 🎲
+     emoji
+
+3. [ ] Shopping List with sort-by-category and budget tracking. These should be
        3 different patterns (shopping list, category list, and budget tracker)
        and a final pattern that combines them together and acts as a launcher.
    - Components: Shopping list (item input + checkboxes + clear button) +
@@ -16,38 +22,38 @@
    - Features: Add/remove items, assign categories, track prices, sort by
      category, view budget totals, check off purchased items
 
-3. [ ] Calendar
+4. [ ] Calendar
    - Components: Month view with day cells + Event list displayed in calendar +
      Day editor (opens when clicking a day)
    - Data: Events with date, time, description
    - Features: View one month at a time, click day to edit its event list,
      events shown in calendar UI
 
-4. [ ] Fitness Workout Planner
+5. [ ] Fitness Workout Planner
    - Components: Exercise routine builder + Set/rep counter + Progress chart
    - Data: Exercises with sets, reps, weight
    - Features: Track personal records, show strength gains over time
 
-5. [ ] Lunch Voter
+6. [ ] Lunch Voter
    - Components: Restaurant list + Voting buttons + Vote tally display +
      Add/remove restaurant form
    - Data: Restaurants with vote counts
    - Features: Add/remove restaurants, vote for favorites, see most popular
      choice
 
-6. [ ] Study Schedule with Focus Timer
+7. [ ] Study Schedule with Focus Timer
    - Components: Study task list + Time block scheduler + Pomodoro timer + Break
      reminders
    - Data: Study topics, estimated duration, completion status
    - Features: Schedule study sessions, track time spent, enforce breaks
 
-7. [ ] Travel Itinerary with Budget Tracker
+8. [ ] Travel Itinerary with Budget Tracker
    - Components: Activity scheduler + Day-by-day timeline + Expense tracker +
      Budget dashboard
    - Data: Activities with time, location, cost
    - Features: Plan entire trip, track expenses by category, budget warnings
 
-8. [ ] Contact Manager with Birthday Reminders
+9. [ ] Contact Manager with Birthday Reminders
    - Components: Contact list + Upcoming birthdays view + Gift idea notes +
      Calendar integration
    - Data: Contacts with birthdays, gift history

tools/ralph/bin/ralph-smoketest.sh

@@ -28,17 +28,42 @@ done
 # llm command to summarize changes
 LLM="./tools/ralph/bin/llm.sh"
 
-{ printf "Your RALPH_ID is %s.\n\n" "$RALPH_ID"; cat ./tools/ralph/SMOKETEST_PROMPT.md; } | \
+# Extract task for this RALPH_ID from TASKS.md
+TASK=$(awk -v id="$RALPH_ID" '
+/^[0-9]+\. \[ \]/ {
+  task_num = substr($1, 1, length($1)-1)
+  if (task_num == id) {
+    found = 1
+    # Strip the "N. [ ] " prefix from first line
+    sub(/^[0-9]+\. \[ \] /, "")
+    print
+    next
+  }
+}
+found && /^[0-9]+\. \[ \]/ {
+  exit
+}
+found {
+  print
+}
+' ./tools/ralph/TASKS.md)
+
+# If no task found, provide default message
+if [ -z "$TASK" ]; then
+  TASK="You have no task, just exit"
+fi
+
+# Replace <SMOKETEST_TASK> in prompt and pipe to claude
+{
+  printf "Your RALPH_ID is %s.\n\n" "$RALPH_ID"
+  awk -v task="$TASK" '{
+    if ($0 ~ /<SMOKETEST_TASK>/) {
+      print task
+    } else {
+      print $0
+    }
+  }' ./tools/ralph/SMOKETEST_PROMPT.md
+} | \
 claude --print --dangerously-skip-permissions \
 --verbose --output-format=stream-json 2>&1 | \
 tee -a ./tools/ralph/logs/ralph-claude.log
-
-# Auto-stash changes if any exist
-if [[ -n "$(git status --porcelain)" ]]; then
-  git add -A
-
-  # Generate commit message from staged changes
-  commit_msg=$(git diff --staged | $LLM "Summarize these changes into a short one-line description, output just that one line")
-
-  git stash push -m "$commit_msg"
-fi

tools/ralph/bin/run_smoketest.sh

@@ -1,7 +1,7 @@
 #!/usr/bin/env bash
 
 # Ralph IDs to run smoketests for
-RALPH_IDS="1 2 3 4 5 6 7 8"
+RALPH_IDS="1 2 3 4 5 6 7 8 9"
 
 # Get the directory where this script is located
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"