Session Detection
How Irrlicht discovers and tracks AI coding agent sessions.
Detection Methods
Irrlicht uses three complementary methods to detect and track sessions. Together they provide fast, reliable discovery from the moment a process starts until the session ends.
Filesystem Watching
- Technology: fsnotify (kqueue on macOS)
- Recursively watches transcript directories for changes
- Events:
CREATE-- new session,WRITE-- activity,REMOVE-- session ended - Filters: only
.jsonlfiles, ignores files older than max age (5 days default)
Process Scanning
- Polls
pgrep -x claudeevery 1 second - Creates pre-sessions (
proc-<pid>) before transcripts exist - Discovers CWD via
lsof -a -p <pid> -d cwd - Pre-sessions are replaced by real sessions when the transcript arrives
Process Exit Monitoring
- kqueue
EVFILT_PROCNOTE_EXITfor instant (~1ms) exit detection - Fallback: periodic liveness sweep via
syscall.Kill(pid, 0)every 5s - Startup cleanup: synchronous dead PID check in
seedFromDisk()
Supported Agents
Claude Code
- Transcript location:
~/.claude/projects/<project>/<session-id>.jsonl - Flat directory structure (one level under
projects/) - Adapter name:
claude-code
OpenAI Codex
- Transcript location:
~/.codex/sessions/YYYY/MM/DD/<session-id>.jsonl - Deep directory structure (recursive watching)
- Adapter name:
codex - Model detection from
~/.codex/config.toml
Pi Coding Agent
- Transcript location:
~/.pi/agent/sessions/--<cwd-dashed>--/<timestamp>_<uuid>.jsonl - JSONL v3 format — session header on first line with
cwd,parentSession, andversionfields - Messages use
rolefield:user,assistant,toolResult,bashExecution - Turn completion detected from
stopReason: "stop"on assistant messages - Adapter name:
pi - Model detection from
~/.pi/agent/settings.json(defaultModelfield) - Supports multiple LLM providers (Anthropic, OpenAI, Google, xAI, Groq)
PID Discovery
| Phase | Mechanism |
|---|---|
| Discovery | lsof -t <transcript> with retry at 500ms, 1s, 2s intervals |
| CWD fallback | If lsof fails, matches claude processes by working directory |
| Registration | kqueue EVFILT_PROC NOTE_EXIT |
| Liveness sweep | syscall.Kill(pid, 0) every 5s |
| Startup cleanup | Synchronous in seedFromDisk() |
Subagent Detection
When Claude Code spawns subagents (via the Agent tool), each subagent creates its own transcript file at:
~/.claude/projects/<project>/<parent-session-id>/subagents/<agent-id>.jsonl
The daemon detects these files through the same filesystem watcher and derives the parent-child relationship from the path structure. Each subagent becomes an independent session with its own state machine, linked to the parent via parent_session_id.
Lifecycle
- Detection: Filesystem watcher sees the new
.jsonlfile in thesubagents/directory - Tracking: Session created with
parent_session_idset; exempt from orphan cleanup (no PID of its own) - Display: Parent session shows a purple badge with the count of active subagents
- Cleanup: Child sessions are deleted when they finish (ready state), when their transcript becomes stale (>2min), or when the parent session is deleted (cascade)
In-Process vs File-Based
Claude Code runs two types of subagents:
- In-process (Explore, Plan) — detected via open
Agenttool calls in the parent transcript; no separate file - File-based (background agents, worktree agents) — create their own transcript in the
subagents/directory
The API's SubagentSummary merges both types into a single count.
Session ID
- File-based: UUID extracted from the filename (
<uuid>.jsonl) - Process-based:
proc-<pid>format, used for pre-sessions before a transcript file is found
Git Metadata
- Branch:
git rev-parse --abbrev-ref HEAD(stripsworktree-prefix) - Project name: derived from
git-common-dir(works correctly with worktrees) - CWD: tail-reads the last 32KB of the transcript to find the latest working directory
Transcript Parsing
The tailer reads JSONL transcripts line by line and extracts:
- Model name -- normalized from various format variations
- Token counts -- input, output, cache read, cache creation
- Tool call state -- open/closed tracking with tool names
- Context window size -- used for utilization pressure calculation
- Cost estimation -- computed from token breakdown and model pricing tables