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.
- 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.
rqd6f4g6zn-bit
666ghj
ghostubborn