Closes#624, #622, #601, #599, #577
## LLM JSON parsing (#624 / #622 / #601)
- New `_parse_llm_json()` in llm_client.py with 5-stage fallback:
1. Strip markdown fences (existing)
2. Strict json.loads (fast path)
3. json.JSONDecoder.raw_decode (handles trailing prose after JSON)
4. Balanced-brace extraction (leading prose + embedded JSON)
5. Strip control chars + retry
- Replaces strict json.loads in chat_json() that was failing on any LLM
appending text after the JSON (common with qwen-plus, ollama, gemma even
with response_format=json_object).
- Logs which fallback was used so problematic LLMs are visible.
- 8 unit-test cases covering each strategy.
## Report section tool_call leak (#599)
- New `_sanitize_section_content()` in report_agent.py detects when a
section's "final answer" is actually an unexecuted tool_call JSON
(e.g. `{"name":"quick_search","parameters":{...}}`) and replaces it
with a clear fallback message instead of writing the raw artifact to
the report.
- Applied at all 3 places where final_answer is returned in
write_section(): the Final Answer path, the no-prefix fallback, and
the force-finalize path.
## Chat history duplicate user message (#577)
- In report_agent.py chat(), defensively dedupe chat_history:
- Only keep {role, content} from history items
- Skip entries that match the current message exactly
- This prevents LLM from seeing a duplicate trailing user message and
echoing back the previous answer.
- Added debug log of constructed messages array for diagnostics.
Background threads (graph building, simulation prep, report generation,
profile generation) now inherit the requesting user's locale preference.
Previously these fell back to 'zh' because Flask request context was
unavailable in spawned threads.
Ensure poster_type stays PascalCase English and stance stays English enum
values regardless of language setting. Only natural language fields follow
the user's language preference.
The language instruction was causing LLM to change entity/relation naming
conventions. Now explicitly enforce PascalCase/UPPER_SNAKE_CASE for technical
identifiers while only applying language preference to description fields.
- Implemented `_get_report_id_for_simulation` to find the most recent report ID associated with a simulation ID by scanning the reports directory.
- Updated `get_simulation_history` to include the retrieved report ID in the response, enhancing the simulation data returned to the client.
- Updated simulation history retrieval to read project details directly from the Simulation file.
- Improved simulation configuration handling by reading simulation requirements from JSON.
- Added project file listing to the simulation history, displaying up to three associated files.
- Refined card layout in HistoryDatabase.vue to accommodate new file display features and improved responsiveness.
- Deleted docker-compose.yml, backend Dockerfile, frontend Dockerfile, and nginx configuration to streamline project setup.
- Updated .env.example to reorganize LLM and ZEP API configurations for clarity and ease of use.
- Enhanced README.md to reflect changes in project structure and provide clearer setup instructions.
- Created package-lock.json for dependency management.
- Updated package.json and frontend package.json to version 0.1.0.
- Adjusted backend pyproject.toml to reflect version 0.1.0.
- Introduced uv.lock for Python dependency resolution.
- Modified the backend setup script to clear the virtual environment before installation.
- Improved README.md by restructuring the prerequisites section into a table for better readability.
- Added installation instructions for the `uv` package and clarified terminal requirements post-installation.
- Updated .env.example to reflect new LLM configuration with Aliyun's API.
- Enhanced .gitignore to include additional files and directories for better exclusion of sensitive and build artifacts.
- Added docker-compose.yml for streamlined deployment of backend and frontend services.
- Introduced Dockerfiles for both backend and frontend to facilitate containerized builds.
- Created README.md to provide comprehensive project documentation and setup instructions.
- Established nginx configuration for frontend to support API proxying and static file serving.
- Decreased the maximum tool calls per section from 8 to 5.
- Reduced the maximum iterations in the ReACT loop from 8 to 5, streamlining the report generation process.
- Deleted the backend README.md file as it was no longer needed.
- Changed the favicon from a SVG to a PNG format for better compatibility.
- Updated the page title in index.html to reflect a more concise branding message.
- Reduced maximum tool calls per chat from 5 to 2 for improved efficiency.
- Simplified system prompt to focus on concise responses and report content.
- Implemented report content retrieval with length limitation to prevent context overflow.
- Adjusted tool call execution to limit to one call per iteration, enhancing clarity in responses.
- Updated user message prompts to encourage concise answers based on retrieved data.
rqd6f4g6zn-bit
666ghj
rqd6f4g6zn-bit
ghostubborn