Fix Markmap table rendering and stabilize Codex model integration for AI mind map generation #45
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
- Add table_to_markmap_tree() and convert_tables_in_markmap() functions - Integrate automatic conversion in AI mind map generation - Update prompt to guide AI away from table format - Add tool script for converting existing mind map files - Preserve tables inside code blocks (as documentation examples) Fixes issue where Markdown tables were rendered as plain text in Markmap, causing nodes to be too wide and reducing readability. Tables are now converted to hierarchical tree structures that Markmap can properly visualize.
- Change DEFAULT_MODEL from gpt-5.2-coding back to gpt-5.2 - Update model name in mindmap_ai_config.toml - Update model recommendations in prepare_llm_input.py
- Change DEFAULT_MODEL from gpt-5.2 to gpt-5.1-codex - Update model name in mindmap_ai_config.toml - Update model recommendations in prepare_llm_input.py - GPT-5.1-codex is optimized for code and structured content generation
…letion models - Remove incorrect -codex pattern from completion model detection - GPT-5.1-codex and GPT-5.2-codex are chat models using /v1/chat/completions - Only legacy text-* models are completion models - Fixes 404 error when using gpt-5.1-codex with completions endpoint
- Remove all Chinese comments from mindmap_ai_config.toml - Always display both prompt and mindmap model configuration at start - Show model name when generating each language version - Improve visibility of which models are being used during generation
- Remove all Chinese comments from mindmap_ai_config.toml - Always display both prompt and mindmap model configuration at start - Show model name when generating each language version - Improve visibility of which models are being used during generation
Update is_chat_model() to treat models containing "codex" (e.g., gpt-5.1-codex) as completion models that use /v1/completions endpoint instead of /v1/chat/completions. This fixes the 404 error when using gpt-5.1-codex model.
- Updated openai version from >=1.0.0 to >=2.11.0 - Version change reflects SDK upgrade from 2.9.0 to 2.11.0
lufftw
commented
Dec 13, 2025
Owner
Author
lufftw
left a comment
lufftw
left a comment
There was a problem hiding this comment.
Tested locally — works as expected.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
This PR consolidates multiple fixes, refactors, and configuration updates to improve
both Markmap mind map rendering quality and LLM model handling stability,
with a focus on Codex-based workflows.
🧠 Mind Map Rendering Improvements
causing excessively wide nodes and poor readability.
table_to_markmap_tree()convert_tables_in_markmap()🤖 Codex & Model Handling Fixes
temperaturewhen calling Codex via Responses API.DEFAULT_MODEL,mindmap_ai_config.toml, and model recommendations consistently.🧹 Configuration & Maintenance
>=2.11.0to match current API behavior.✅ Result