chat() and chat_json() now delegate think-tag stripping and JSON
cleanup to Prompture's built-in utilities (strip_think_tags,
clean_json_text). Manual regexes are kept only in the OpenAI
fallback path. Adds LM Studio integration test script.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add optional Prompture integration for 12+ LLM providers (LM Studio,
Ollama, Claude, Groq, Kimi/Moonshot, etc.) as a drop-in backend.
Zero breaking changes — falls back to the existing OpenAI SDK client
when Prompture is not installed.
- Rewrite llm_client.py with dual-backend architecture
- Update .env.example with provider/model format examples
- Add multi-provider table to README Quick Start section
- Add prompture as optional dependency in requirements.txt
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
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.
LM Studio and Ollama do not support response_format: json_object,
only json_schema or text. This causes errors when using local LLMs.
The existing markdown fence cleanup logic in chat_json() already
handles parsing JSON from raw LLM output, making response_format
unnecessary. This change follows the same pattern as commit 985f89f
which improved compatibility with diverse model outputs.
Tested with: LM Studio + qwen3.5-9b (full predict pipeline passes)
- 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.
- 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.
- 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.
- Increased the maximum tool calls per section from 4 to 8, enhancing the agent's capabilities.
- Raised the maximum reflection rounds from 2 to 3 to allow for deeper analysis.
- Adjusted the maximum tool calls per chat from 3 to 5 for improved interaction.
- Expanded the maximum agents for interviews from 5 to 20, facilitating more comprehensive data gathering.
- Increased the maximum iterations for ReACT loops from 5 to 8 and from 3 to 5 in different contexts, optimizing the report generation process.
- Updated the `to_text` method in the `PanoramaResult` class to provide complete outputs for current facts, historical facts, and involved entities, improving data visibility.
- Modified the `to_text` method in the `AgentInterview` class to display the full agent bio without truncation.
- Adjusted the `ZepToolsService` class to retrieve all related entity details and facts without limiting the output, ensuring comprehensive data representation.
Lucas Ercolano
Juan Denis
BaiFu
ghostubborn
MiroFish Bot
iml1s