Critical fix for activity model configuration:
- Handle MODEL_1, MODEL_2, MODEL_3 references in get_openai_client_and_model()
- Look up MODEL_ENDPOINT_{n}, MODEL_API_KEY_{n}, MODEL_NAME_{n} from environment
- Fall back gracefully to default model if MODEL_{n} not configured
- Matches implementation in research/guarded_ai.py
Fixes error: 'NoneType' object has no attribute 'chat'
This error occurred when activities tried to use classifier_model="MODEL_1"
but the app didn't know how to resolve the MODEL_X reference.
Now activity37 (programming languages) will work correctly with:
- classifier_model: "MODEL_1" (Hermes for classification)
- feedback_model: "MODEL_3" (Qwen3-Coder for code generation)
Critical fix for guarded_ai.py:
- Add MODEL_NAME_{n} environment variable support
- Fixes hard-coded "model" string that breaks Azure OpenAI and other endpoints
- Falls back to "model" if MODEL_NAME_{n} not specified
- Some endpoints require actual deployment name in model parameter
Validator improvement:
- Allow feedback_prompts as alternative to feedback_tokens_for_ai
- Prevents false warning when using metadata_feedback_filter with new prompt system
Documentation:
- Added MODEL_NAME_{n} examples to CLAUDE.md
- Documented that Azure and similar endpoints need this variable
All 8 activities validated: 0 errors, 0 warnings
Added comprehensive Activity YAML Schema section covering:
- Model Configuration feature (classifier_model and feedback_model)
- Why separate models (speed, quality, cost, flexibility)
- Model defaults (MODEL_1/Hermes as universal default)
- Recommended model combinations table
- Environment variable configuration
- Example programming activity with dual models
- Activity YAML validation instructions
- CLI testing with model configuration
- Qwen3-Coder-30B setup guide (llama.cpp and ollama)
This documents the new dual-model architecture that allows:
- Fast classification with Hermes (8B)
- Specialized feedback with domain models (e.g., Qwen3-Coder 30B)
- Activity and step-level model overrides
Transformed planning document into comprehensive completion report:
- Status: 8 activities completed (30-37), 6,112 lines of YAML
- Documented new classifier_model and feedback_model feature
- Added model setup guide for Qwen3-Coder-30B
- Detailed activity summaries with special features
- Technical architecture and implementation decisions
- Usage examples and future enhancements
Key highlights:
- All activities validated with 0 errors
- Dual-model architecture explained
- Activity 37 flagship feature: universal programming language support
- Hermes excellence in role-playing scenarios
Added detailed comments showing how to use the recommended model:
- hf.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF:Q4_K_M
- Setup instructions for llama.cpp (with GPU offloading)
- Alternative setup with ollama
- Environment variable configuration examples
This 30B parameter model is specifically optimized for code generation
across all programming languages, making it perfect for the universal
programming activity.
Changes:
- Enhanced get_openai_client_and_model() to support MODEL_X references
- Added model parameter (default "MODEL_1") to all AI functions:
- categorize_response()
- generate_ai_feedback()
- provide_feedback()
- provide_feedback_prompts()
- translate_text()
- Updated simulate_activity() to:
- Read classifier_model and feedback_model from YAML
- Support step-level model overrides
- Pass appropriate models to classifier vs feedback functions
This ensures the CLI simulation tool matches the production activity.py behavior.
Hermes is always available in every install, making it the perfect default.
All model parameters now default to "MODEL_1" instead of None:
- classifier_model: Fast, accurate classification
- feedback_model: Great for role-playing and general feedback
Activities can still override these defaults:
- At activity level for all steps
- At step level for specific interactions
This ensures activities work out-of-the-box without requiring model configuration.
Allow activities to specify separate models for classification and feedback:
- classifier_model: Used for categorizing user responses into buckets
- feedback_model: Used for generating AI feedback and translations
Both fields can be set at activity level (defaults) and overridden at step level.
Updated activity37 to use:
- MODEL_1 (Hermes) for classification
- MODEL_3 (Qwen 3 Coder) for feedback
This allows using specialized models for different tasks, e.g., fast classification
with accurate feedback generation from domain-specific models.
Created 3 comprehensive educational activities without embedded Python:
1. activity35-american-history.yaml - Advanced American History for gifted students
- Founding principles and Constitutional design
- Civil War causes and Reconstruction failure
- Civil Rights Movement strategies
- Primary source analysis and critical historical thinking
- Connects past to present issues
2. activity36-biblical-history.yaml - Biblical History & Ancient Near East
- Ancient Near Eastern context (Mesopotamia, Egypt, Canaan)
- Archaeological evidence and historical reconstruction
- Israelite history (Exodus, Monarchy, Exile)
- Roman period and early Christianity
- Foundation myths vs historical facts
- Cultural adaptation and religious transformation
3. activity37-programming-languages.yaml - Universal Programming Concepts
- Student chooses ANY programming language (Python, C++, COBOL, anything)
- AI adapts all examples/feedback to chosen language via metadata
- Covers: stdout/output, variables, data types, control flow, loops, functions
- All examples use stdout to display messages
- Concepts applicable to every language
- Language-specific syntax provided by AI
All activities:
- Use only YAML features (no embedded Python)
- Validate successfully with 0 errors
- Provide sophisticated educational content
- Use AI feedback for personalization
- Include critical thinking and reflection
- Track progress via metadata
Total: 8 new educational activities across 2 commits (5 from previous commit + 3 now)
Created 5 comprehensive educational activities that use only YAML features
(buckets, transitions, metadata operations, AI feedback) without Python scripts:
- activity30-logic-puzzles.yaml: Critical thinking through deductive reasoning,
contrapositives, syllogisms, and knights/knaves puzzles
- activity31-scientific-method.yaml: Learn scientific method through historical
case studies (Semmelweis, Newton) and experimental design principles
- activity32-world-geography.yaml: Choose-your-own-adventure journey exploring
continents, countries, capitals, and cultural facts
- activity33-environmental-science.yaml: Role-playing as environmental consultant
making sustainability decisions on transportation, energy, land use, waste, and food
- activity34-media-literacy.yaml: Develop critical media consumption skills,
evaluate sources, recognize bias, fact-check claims, and spot manipulation
All activities:
- Follow existing YAML schema and validate successfully
- Use Socratic buckets for educational feedback
- Include set_language support
- Track progress via metadata
- Provide AI-generated personalized feedback
- Are educational, engaging, and progressively challenging
- Include final reflection steps
Also added NEW_ACTIVITIES_PLAN.md documenting the planning process and
design rationale for each activity.
Added CSS variables for link colors with better contrast:
- Light mode: #0066cc (normal), #004499 (hover)
- Dark mode: #58a6ff (normal), #79b8ff (hover)
Applied general link styling rules that adapt to both themes,
ensuring links are clearly visible and distinguishable in dark mode.
Added CSS variables for code execution result colors that adapt to theme:
- --text-info: Blue for informational text (language labels)
- --text-success: Green for successful output
- --text-error: Red for errors and warnings
Updated JavaScript to use CSS variables instead of hard-coded colors,
ensuring proper contrast and readability in both light and dark modes.
Address CodeRabbit feedback by replacing bare except clauses with
specific Exception handling:
- test_activity_integration.py: Fix 2 tearDown methods
- test_app_integration.py: Fix 1 tearDown method
Changes:
- Replace bare 'except:' with 'except Exception as e:'
- Add explanatory comments for why exceptions are caught
- Maintain same functionality while improving code quality
Tests still pass: 11/13 integration tests passing (85%)
- Switch from default highlight.js theme to GitHub themes
- Use github-dark theme for dark mode with better color contrast
- Use github theme for light mode
- Dynamically switch themes when user toggles dark/light mode
- Apply correct theme on page load based on saved preferences
- Moved all theme-related inline styles to CSS rules
- Created proper selectors for labels, inputs, and buttons
- Added utility-belt class to mobile menu for consistent styling
- Removed redundant inline style attributes
Major improvements to test_activity_integration.py:
- Configure tests to use uncloseai.com models (hermes-3-llama-3.1-405b and qwen-2.5-72b)
- Fix Flask app and activity module configuration in test setUp
- Properly initialize MODEL_CLIENT_MAP with test models
- Set up activity.app, activity.db, and activity.get_room for proper test isolation
- Fix file path handling in create_test_activity_file()
- Improve activity YAML structure to avoid premature activity completion
- Add session refresh to handle database state properly
Test results improved from 3/9 passing to 7/9 passing (78% pass rate):
✓ test_cancel_activity
✓ test_display_activity_metadata
✓ test_execute_processing_script_with_metadata_operations
✓ test_handle_activity_response_correct_answer
✓ test_start_activity
✓ test_activity_state_metadata_persistence
✓ test_metadata_update_and_remove
Remaining issues (edge cases):
- test_handle_activity_response_increments_attempts: attempts counter behavior on incorrect answers
- test_loop_through_steps_until_question: step navigation emit count
- Added CSS variables for light and dark themes
- Implemented theme toggle buttons in both desktop sidebar and mobile menu
- Added JavaScript logic to switch themes and persist choice in localStorage
- Applied dark theme styling to all UI elements including code blocks
- Theme is applied immediately on page load to prevent flash
- Add pytest.ini configuration for better test organization
- Fix test file naming conflicts (rename test_guarded_ai.py)
- Improve database test setup in conftest.py with proper fixtures
- Remove duplicate test_app_feedback.py (functionality covered in test_guarded_ai_functions.py)
- Fix database initialization issues in integration tests
- All working tests now passing (120 passed, 65% coverage)
- Switch from sync /execute to async /execute/async with polling
- Poll intervals: 300ms, 750ms, 1450ms, 2350ms, 3000ms, 4600ms, 6600ms+
- Show cancel button after 3 seconds if job still running
- Display partial output when cancelled or timed out
- Add Copy and Run buttons to bottom of truncated code blocks (next to Show More)
- Prevents accidental cancels and DoS from spam-clicking
Moved all activity-related functions from app.py to a new activity.py
module to improve code organization and maintainability. This reduces
app.py from 2852 lines to 1552 lines.
Changes:
- Created activity.py with 16 activity-related functions
- Updated app.py to import and initialize activity module
- Updated test_app.py to import activity module
- All 34 unit tests pass successfully
Pass the selected model parameter through the entire activity workflow
to ensure all AI operations (categorization, translation, feedback
generation, and grading) use the user's chosen model instead of
defaulting to the system default. Falls back to default when no model
is selected.
- Add copy button after edit button for all messages
- Fix model/voice settings persistence when creating new rooms
- Save model/voice selections to localStorage for better state management
- Ensure settings are loaded from localStorage if not in URL parameters
- Remove duplicate messages from section transitions like activity14
- Fix coin categorization issue - 'use coin' was being misclassified as 'use_key_and_password'
- Add section_4:step_2 for post-safe-opening state with proper coin slot options
- Update tokens_for_ai to properly distinguish between different user actions
- Now players can properly access the secret compartment using the coin
- Activity validated and passes all checks
- Remove STFU check from app.py feedback filtering logic
- Update tests to remove STFU-specific test cases
- Simplify empty content filtering to just check for actual content
Remove prescriptive ship destruction descriptions and let the AI be creative.
Since skip_condition ensures these prompts only run when ships are actually
destroyed, we can make the prompts more concise and focused on the outcome.
Add skip_condition logic to feedback prompts to prevent AI from generating
false ship destruction messages when no ships were actually destroyed.
Changes:
- Add skip_condition parameter support in provide_feedback_prompts()
- Support all_null, all_false, and all_true condition types
- Apply skip_condition to battleship Ship Status and Game Over prompts
- Add comprehensive unit tests covering all skip condition scenarios
- Test real battleship scenario that was causing hallucinations
This prevents the AI from creating false positive ship destruction messages
when metadata indicates no ships were actually sunk (all null values).
Voice Persistence:
- Add voice/model saving to localStorage for persistent settings
- Load voice from URL → localStorage → default priority order
- Voice selection now persists across browser sessions and page refreshes
Dynamic Room Links:
- Add updateRoomLinksWithCurrentParams() function to update sidebar room links
- Room links now dynamically update with current username, model, and voice settings
- Both desktop and mobile room links stay synchronized with current parameters
- Fixes issue where clicking room links would lose user's current settings
Technical improvements:
- Enhanced syncInputsAndQueryString() to save to localStorage and update room links
- Initial sync call on page load ensures proper state from the start
- Maintains backwards compatibility with existing functionality
- Deleted test_streaming_protocol_simple.py (317 lines)
- Keeping test_streaming_protocol.py (541 lines) with comprehensive coverage
- Eliminates duplicate testing of the same functionality
- Consolidates streaming tests into single authoritative file
- Add username field to right sidebar and mobile modal with 'guest' default
- Implement real-time username sync with URL query string updates
- Add opencompletion.com button and new room creation in left sidebar
- Implement room name slugification (e.g. "a whole new world" → "a-whole-new-world")
- Create shared utils.js for common functions like slugify
- Add single search result auto-redirect functionality
- Remove redundant UI elements ("Create New Room" header, docs link)
- Preserve user settings (username, model, voice) across redirects and room creation
Technical improvements:
- Consolidated duplicate code into shared utility functions
- Enhanced search logic with parameter preservation
- Improved mobile/desktop sync for all input fields
- Better URL handling and query string management
- Separate username/model header from message content using distinct DOM elements
- Fix button positioning to appear on left side of messages
- Ensure TTS only reads clean message content, not username/model header
- Add support for stopping current TTS when auto-play is toggled off
- Improve DOM structure with message-body wrapper for proper layout
- Fix streaming messages to maintain header display throughout entire stream
- Created test_streaming_protocol_simple.py with 3 passing tests
- Created test_streaming_protocol.py with comprehensive test suite
- Tests verify new protocol format with separate username/model fields
- Tests confirm content separation from metadata for clean TTS processing
- Added debug logging for Game Over feedback prompt
- All tests validate the streaming refactoring works correctly
Backend changes:
- Send username, model_name, and is_first_chunk as separate fields
- Keep actual content separate from header formatting
- Cleaner separation of concerns in streaming protocol
Frontend changes:
- Build display content with header only for visual rendering
- Keep messageBuffers clean (content only) for TTS processing
- TTS now processes pure content without username headers
This fixes the issue where TTS was reading 'fxhp (model):' prefix
- Fixed querySelector to find Play button specifically, not first button
- Regular messages used Array.from().find() correctly
- Streaming messages were using querySelector('button') which found Delete button
- This explains why streamed messages never got added to TTS queue
- Added console.log statements to streaming TTS logic
- Will help identify why streamed messages aren't being added to TTS queue
- Debug info includes autoPlayTTS state, completion status, buffer content
- Removed feedback_tokens_for_ai from step 3 Game Over
- Exit transition already has appropriate content_blocks
- Eliminates duplicate farewell messages when exiting
- Added activity_status emit with active: false when activity ends
- Now matches behavior of activity cancellation
- Users will automatically see activity chooser when activity finishes
Major improvements to battleship game feedback accuracy and user experience:
## New Multi-Prompt Feedback System
- Replaced single feedback with 3 specialized prompts: Shot Report, Ship Status, Game Over
- Each prompt has individual metadata filtering to see only relevant data
- Shot Report only sees hit/miss data, Ship Status only sees ship destruction data
- Added STFU token system to suppress empty messages (filtered out automatically)
## Technical Implementation
- Added per-prompt metadata_filter support in YAML structure
- Updated app.py and guarded_ai.py to handle prompt-specific filtering
- Legacy single-prompt system still works with transition-level filtering
- Added comprehensive test suite for feedback system validation
## User Experience Fixes
- Fixed TTS queue blocking JavaScript execution (async promises instead of await)
- Ship Status now correctly reports who destroyed which ship (role confusion fixed)
- Game Over only appears when game actually ends (no more random messages)
- Maintained dramatic storytelling while ensuring factual accuracy
## Battleship-Specific Improvements
- Ship destruction messages only appear when ships actually sink
- Clear separation of concerns: hits/misses vs ship destruction vs game over
- Eliminated false positive ship destruction reports
- Fixed role reversal where wrong player got credit for destruction
The battleship narrator now provides accurate, contextual feedback while preserving the dramatic naval warfare atmosphere.
- Fix battleship feedback perspective confusion with better Hermes prompting
- Add auto-play TTS button with localStorage persistence and queueing system
- Move activity controls below model/voice selectors in sidebar
- Add activity controls to mobile hamburger menu
- Fix model/activity dropdowns to stay within container bounds
- Filter activities API to only show .yaml/.yml files
- Clean up system message labels by moving to usernames (System (Feedback), System (Question))
- Apply black formatting to app.py
