feat(parser): split Gemini CLI thoughts into separate thinking messages #103
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 support for parsing and displaying XML command blocks from Claude Code JSONL files (e.g., /clear, /help, /model commands). Changes: - Add SlashCommand variant to MessageType enum - Add SlashCommandData struct with command_name, message, args, stdout fields - Add regex parsing in claude_code.rs for XML command blocks - Add database migration 017 for slash_command message type - Add yellow/amber styling in TUI for slash command messages - Add SlashCommandMessage component in React GUI - Add unit tests for slash command parsing - Fix clippy large_enum_variant warning by boxing MessageGroup fields 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <[email protected]>
….com:wafflestudio/retrochat
Gemini CLI data compacts thinking, tool use, and AI message content into a single message object with a `thoughts[]` array. This differs from our schema which expects thinking to be separate messages with `MessageType::Thinking`. Changes: - Modified `convert_session_message` to return `Vec<Message>` instead of single `Message` - Create separate `MessageType::Thinking` messages from each thought in the `thoughts[]` array before the main message - Format thinking content as `**subject**\n\ndescription` - Use thought's timestamp with fallback to main message timestamp - Only process thoughts for Assistant messages (ignore on User) - Use index for thinking message UUID to avoid collision - Updated callers to handle multiple messages with proper sequence numbering 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <[email protected]>
sanggggg
force-pushed
the
feat/gemini-thinking-messages
branch
from
ccf1b51 to
16f4988
Compare
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.
Summary
Gemini CLI data compacts thinking, tool use, and AI message content into a single message object with a
thoughts[]array. Our schema expects thinking to be separate messages withMessageType::Thinking. This PR aligns Gemini CLI parsing with our schema design.Changes
convert_session_messageto returnVec<Message>instead of singleMessageMessageType::Thinkingmessages from each thought in thethoughts[]array**subject**\n\ndescriptionparse_messages_with_filename_session_id,parse_session_format) to handle multiple messages with proper sequence numberingtest_parse_gemini_session_with_thoughts- verifies thinking messages are created correctlytest_parse_gemini_session_no_thoughts- regression testtest_parse_gemini_session_user_message_ignores_thoughts- confirms user thoughts are ignoredExample Result
Test Plan
🤖 Generated with Claude Code