feat(acp): Discover session transcripts for parsing #150
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
Plan covers: - Session discovery module to find transcript files - Exposing session_id from AcpBackend to TUI - Integrating token usage into /status command - Edge case handling for missing/malformed transcripts
Add session_discovery module that locates transcript files based on agent type and session ID. Supports Claude, Codex, and Gemini agents with different directory layouts: - Claude: ~/.claude/projects/<PROJECT_PATH>/<SESSIONID>.jsonl - Codex: ~/.codex/sessions/<YEAR>/<MM>/<DD>/rollout-*-<GUID>.jsonl - Gemini: ~/.gemini/tmp/<HASHED>/chats/session-*-<ID>.json Includes comprehensive tests using TDD approach.
Store the AgentKind from agent config and expose via agent_kind() method. This enables downstream code to determine which agent type (Claude, Codex, Gemini) is running for session transcript discovery.
- Add TokenUsageCell to render token usage report in session header - Add AcpSessionInfo struct and GetSessionInfo command to AcpAgentHandle - Integrate session discovery and transcript parsing into /status - Add From<registry::AgentKind> impl for session_parser::AgentKind When /status is invoked, the TUI now asynchronously: 1. Gets session info (agent kind, session ID) from ACP handle 2. Discovers the transcript path using session_discovery module 3. Parses token usage from the transcript 4. Displays input/output/total tokens with context window usage
- Replace path.is_dir() with entry.file_type().await to avoid blocking the async runtime in find_file_with_suffix - Remove @current-session markers from session discovery tests - Apply cargo fmt and clippy fixes
- Add test_status_displays_token_usage_from_session_transcript E2E test - Verifies /status displays token usage from Claude session transcript - Uses session-claude.jsonl fixture placed in expected Claude directory structure - Test waits for async transcript discovery and parsing to complete - Validates Token Usage header and token count labels appear in output This test documents the session transcript discovery feature implemented in this branch (session ID discovery + transcript path resolution + parsing).
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.
No description provided.