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>
- Add sans-serif font for English left-pane (status, workflow sections)
- Shorten English workflow step descriptions
- Reduce English report title font-size from 36px to 28px
- Use sans-serif font for English titles, descriptions and navbar
- Shorten English hero text to avoid overflow
- Fix :global() scoped CSS issue that was setting root font-size to 3.5rem
- Use separate unscoped style block for html[lang] selectors
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)
- Added VITE_API_TIMEOUT environment variable support
- Default remains 300000ms (5 minutes)
- Users can increase timeout for slow local models like Ollama
- Example: VITE_API_TIMEOUT=600000 for 10 minutes
Fixes#58
Lucas Ercolano
Juan Denis
666ghj
ghostubborn
iml1s
Jason