Repository navigation
fix(chat): cite with [N] and keep list numbering - #86
Merged
Merged
Conversation
The Brain base prompt told models to cite "[obsidian:file.md]" while the context block asked for "[N]"; MiniMax followed the first, so answers showed raw source tags. The base prompt now asks for the excerpt number; the tool-calling path (no numbered excerpts) keeps the source style. chat.js renders source-style cites as a chip, nests indented sub-items inside the item above, and keeps an ordered list's first number, so a bullet between "1." and "2." no longer restarts the count at 1. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Codex Review SummaryThis comment shows the latest Codex review activity on this pull request.
ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings. |
|
You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard. |
Team cards and the CEO's answer under "And beyond your notes", plus a Brain answer from a real model (10-brain-answer.png) for the launch gallery. Fictional vault, MiniMax-M3, taken with the fixes in this PR. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Found while taking team-mode screenshots with a real model (MiniMax-M3).
Citations. The Brain base prompt said "append the source like [obsidian:filename.md]" while every context block says "cite with [N]". MiniMax followed the first, so answers showed raw
[obsidian:Pricing experiment.md]tags instead of the numbered chips. The base prompt now asks for the excerpt's number. The tool-calling path inserver.pyhas no numbered excerpts, so it appends the source-style instruction itself.Renderer (
chat.js).[obsidian:…],[repo:…],[memory:…]…) render as a chip with the note name, for older threads and models that still do it.<ol>.start=), so a bullet between "1." and "2." no longer restarts the count at 1. Blank lines between items stay one list.Tests. New
tests/test_chat_markdown_js.pyruns the renderer under Node (lists, nesting, both cite styles, escaping). Full suite: 2120 passed, 29 skipped. One deselected test,test_media_providers.py::test_a_missing_fastembed_is_not_retried_on_every_call, fails onmaintoo on a machine that has fastembed installed withHF_HUB_OFFLINE=1; it is unrelated.🤖 Generated with Claude Code