Fix streaming issues that caused text repetition and broken tool execution
in Open WebUI. Implements real LLM streaming using PydanticAI's run_stream()
with delta=True instead of artificial word-by-word chunking.
**Fixed:**
- Text repetition in streaming output (was accumulating instead of deltas)
- Broken tool execution (tools now execute properly in streaming mode)
- Invalid 'thinking' parameter in ReasoningOutputItem schema
**Changes:**
- Add run_with_scoped_tools_stream() method to TatlockAgent
- Uses PydanticAI's run_stream() with delta=True for real deltas
- Properly streams LLM output with tool execution
- Update StreamingCoordinator.stream_response_with_steward()
- Uses new streaming method instead of fake word-by-word streaming
- Removes invalid thinking parameter from ReasoningOutputItem
- All streaming now uses actual LLM deltas, not accumulated text
Resolves streaming issues reported in Open WebUI where responses showed
repetitive text and tool calls appeared as raw JSON instead of executed results.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Implements Phases 2, 3, and 6: Complete Responses API implementation
Core API (Phase 2):
- OpenAI Responses API format with structured output items
- Streaming and non-streaming support via SSE-Starlette
- Reasoning items (thinking summaries)
- Function call items (tool execution)
- Message items (assistant responses)
- Router, schemas, service, and streaming coordinator
Conversation History (Phase 3):
- Hybrid client/server approach
- Auto-generated deterministic conversation IDs
- Configurable max turns with automatic trimming
- Context window management with token counting
- Token usage statistics
- Placeholder for future vector memory integration
Advanced Features (Phase 6):
- Parameter validation with Pydantic field validators:
- Temperature: 0.0-2.0 range enforcement
- Reasoning effort: 6 levels (none to xhigh)
- Max output tokens: positive integer enforcement
- Stop sequences: up to 4, non-empty strings
- Real-time stop sequence detection during streaming
- Real-time max tokens enforcement with token counting
- Graceful error handling and OpenAI-compatible error format
Testing:
- 9 unit tests for API endpoints and streaming
- 11 unit tests for error handling
- 13 unit tests for conversation history and context
- 12 unit tests for advanced features and validation
- Total: 45 tests with comprehensive coverage
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
jpmschweitzerandClaude Sonnet 4.5