e14080129e
Fix str.format KeyError by using %-formatting for ontology JSON
2026-03-13 19:22:36 +07:00
b4c7f67b00
Add traceback logging for extraction errors
2026-03-13 19:19:22 +07:00
db6e235b98
Add logging to LLM graph builder for debugging extraction failures
2026-03-13 19:14:36 +07:00
79519ddd54
Replace Zep with direct LLM calls for graph building
...
Add LLMGraphBuilderService that extracts entities/relationships
from text chunks using Groq instead of Zep Cloud API. Graph data
is persisted to disk as graph_data.json, with fallback to Zep
for existing graphs.
2026-03-13 19:07:40 +07:00
034504c92a
Fix page refresh killing running simulations
...
SimulationView was stopping running simulations on every mount,
including page refreshes. Now only stops when user explicitly
navigates back from Step 3 via fromStep3 query param.
2026-03-13 18:40:40 +07:00
943d56d478
Add GPU passthrough for BERT model acceleration
2026-03-13 18:09:48 +07:00
8024cb130a
Fix Groq API compatibility in parallel simulation
...
- Patch camel tool schema to add empty properties when required is
present but properties is missing (fixes do_nothing tool rejection)
- Fix LLM-generated concatenated hour arrays in config loading
(e.g. [19202122] -> [19,20,21,22])
2026-03-13 17:21:30 +07:00
42ab084edd
Translate all backend LLM prompts and API messages to English
2026-03-13 02:47:30 +07:00
d3121637c7
Translate frontend UI to English
2026-03-13 01:55:46 +07:00
5f20558e78
Fix double /api prefix in axios baseURL
2026-03-13 01:08:47 +07:00
2279d2a321
Build from source, fix API base URL to use Vite proxy
2026-03-13 01:04:15 +07:00
761dbddbf9
Set VITE_API_BASE_URL to empty for proxy-based routing
2026-03-13 00:56:01 +07:00
ead97087ac
Use environment vars from Coolify instead of env_file
2026-03-13 00:45:20 +07:00
c20d293e5f
Patch vite allowedHosts at container startup
2026-03-13 00:40:50 +07:00
238a639b01
Allow all hosts in Vite config for reverse proxy
2026-03-13 00:37:15 +07:00
452da00064
Use expose instead of ports for Coolify compatibility
2026-03-13 00:21:20 +07:00
666ghj
985f89f49a
fix: resolve 500 error caused by <think> tags and markdown code fences in content field from reasoning models like MiniMax/GLM
2026-03-06 00:30:31 +08:00
666ghj
a1ff79c0ef
Update README
2026-03-05 23:22:26 +08:00
666ghj
85b03d4f0f
Update README
2026-02-27 17:29:41 +08:00
666ghj
c6cea12774
docs(readme): add live demo section with link to online prediction simulation for both English and Chinese README files
2026-02-27 17:27:49 +08:00
666ghj
da6548e96f
feat(graph): implement pagination for fetching nodes and edges; add utility functions for streamlined data retrieval
2026-02-27 15:53:29 +08:00
666ghj
d30a0a23ef
Update README
2026-02-25 16:16:24 +08:00
666ghj
25aa4f75d2
fix(report_agent): refine tool call handling and response validation; enforce strict separation between tool calls and final answers
2026-02-24 17:47:44 +08:00
666ghj
a795405428
style(home): add overflow-y property to upload zone and adjust alignment for files
2026-02-22 23:40:40 +08:00
666ghj
040c745c86
feat(readme): add Trendshift badge to README files for repository visibility
2026-02-22 23:07:28 +08:00
666ghj
08ec856a58
fix(report_agent): update max_agents parameter description and enforce maximum limit of 10 agents
2026-02-14 18:35:05 +08:00
666ghj
ae1f38cdcc
fix(report_agent): improve markdown rendering by cleaning up <br> tags around block-level elements and enhancing list formatting
2026-02-14 18:25:20 +08:00
666ghj
ddd9ff2479
feat(report_agent): update report language consistency guidelines; ensure all quoted content is translated to the report language for clarity
2026-02-14 18:24:03 +08:00
666ghj
709a0d7023
feat(report_agent): enhance markdown rendering for lists and improve formatting; support nested lists and clean up HTML output
2026-02-14 17:04:04 +08:00
666ghj
7601d78fd4
feat(report_agent): enhance interview text processing and response handling; improve quote extraction and formatting for better clarity
2026-02-14 16:56:48 +08:00
666ghj
dc0a9261d1
feat(report_agent): add detailed tool descriptions and prompts for future prediction report generation
2026-02-14 15:16:17 +08:00
666ghj
d2041f6fb8
fix(report_agent): update description of insight_forge tool to remove "最强大" and enhance clarity
2026-02-14 14:48:23 +08:00
666ghj
0a59bace92
fix(report_agent): increase minimum tool call requirement from 2 to 3 per chapter and enhance user prompts to encourage diverse tool usage
2026-02-06 19:37:52 +08:00
666ghj
e004fe8f14
fix(report_agent): update tool call requirements in content generation to allow up to 5 tool calls per chapter and clarify user prompts for insufficient data
2026-02-06 18:34:19 +08:00
666ghj
f9abaf8e9f
refactor(report_agent, Step4Report): simplify logging and remove subsection handling; update UI to reflect changes in section content generation
2026-02-06 18:13:30 +08:00
666ghj
54f1291967
fix(report_agent): handle None responses from LLM during content generation and enforce fallback behavior
2026-01-29 17:08:39 +08:00
666ghj
0b71f89f96
fix(Step2EnvSetup): update expectedTotal only when API returns a valid value to prevent overwriting existing data
2026-01-29 10:58:36 +08:00
666ghj
40f7035947
fix(config): enable overriding of environment variables when loading .env file
2026-01-23 16:20:24 +08:00
666ghj
93e1a592df
feat(README): add Docker badge to README files for enhanced visibility of Docker support
2026-01-22 19:03:44 +08:00
666ghj
390c120fef
fix(file_parser): handle non-UTF-8 encoded text files with automatic encoding detection
2026-01-22 18:28:37 +08:00
666ghj
0efd9352a0
feat(docker): add Docker support with Dockerfile, docker-compose.yml, and .dockerignore; update README for Docker deployment instructions
2026-01-22 14:35:41 +08:00
666ghj
9556854fbf
refactor(.env.example): update LLM API configuration comments for clarity and add usage note
2026-01-20 18:05:36 +08:00
666ghj
94633e1330
refactor(README): update demo video section titles and clarify LLM API configuration instructions
2026-01-20 18:02:33 +08:00
666ghj
b0e065ed20
refactor(README): update demo video section to include new financial and political prediction examples
2026-01-20 11:25:24 +08:00
666ghj
824e81e1a4
refactor(README): update demo video section titles for clarity and consistency
2026-01-20 11:21:45 +08:00
666ghj
fa19242477
fix(README): update image asset for Dream of the Red Chamber demo video section
2026-01-20 11:18:35 +08:00
666ghj
be2acf663d
feat(README): add demo video sections for Wuhan University Public Opinion and Dream of the Red Chamber simulations; include new image asset
2026-01-20 11:17:11 +08:00
666ghj
57e72250a9
chore(README): remove note about Windows compatibility from prerequisites section.
2026-01-18 22:37:02 +08:00
666ghj
085aa6bbe6
fix(GraphPanel): optimize force graph drag behavior to prevent simulation restart on click
...
Background:
- With many nodes, D3 force simulation tick callback updates all nodes/edges/labels every frame
- Original implementation called simulation.restart() in drag start event on mousedown
- Even after simulation converged, clicking a node to view details would restart simulation, causing lag
Solution:
- Distinguish between "click" and "drag" using 3px movement threshold
- On drag start: only record initial position, do not restart simulation
- On drag event: detect movement exceeding threshold before marking as actual drag and restarting simulation
- Pure click operations no longer trigger simulation restart, keeping graph static
Bug fix:
- Fixed issue where nodes became undraggable after initial optimization
- Cause: incorrectly used if(!event.active) check in drag event
- event.active equals 1 during drag event, causing restart() to never execute
- Removed that condition, using custom _isDragging flag to control logic instead
2026-01-18 22:35:24 +08:00
666ghj
49847c5b26
feat(Step5Interaction): add section number display for improved user navigation
2026-01-16 21:26:11 +08:00
