ktg-plugin-marketplace/plugins/voyage/commands/trekendsession.md

name	description	argument-hint	model
trekendsession	Mark the current session as complete and write session-state pointing at the next session. Helper for informal multi-session flows.	<next-brief-path> <next-label> | --help	sonnet

Voyage End-Session Local v1.0

Tiny helper for informal multi-session flows (no formal plan with Execution Strategy). Writes a .session-state.local.json pointing at the next session so /trekcontinue can resume in a fresh Claude chat.

For formal flows (a plan produced by /trekplan --project), /trekexecute Phase 8 already writes the state file — this helper is unnecessary there. Use this command for ad-hoc release runs, manual multi-session handovers, or any flow that does not run through /trekexecute.

Pipeline position:

... session N work ...
/trekendsession <brief> "<next-label>"   →  writes state
... session boundary, fresh chat ...
/trekcontinue                                         →  reads state, starts session N+1

See Handover 7 in docs/HANDOVER-CONTRACTS.md for the schema.

Phase 0 — --help handling

If $ARGUMENTS contains --help or -h, print the usage block below and exit cleanly. Do NOT proceed to any further phase.

/trekendsession — Mark current session done; point at next session.

Usage:
  /trekendsession <next-brief-path> <next-label>
  /trekendsession --help

Both arguments are REQUIRED. No interactive prompt — headless-safe.

Writes <project-dir>/.session-state.local.json with:
  schema_version           1
  project                  <auto-resolved from cwd>
  next_session_brief_path  <next-brief-path argument>
  next_session_label       <next-label argument>
  status                   in_progress
  updated_at               <now, ISO-8601>

Then validates via lib/validators/session-state-validator.mjs and prints
the same 3-line narration that /trekcontinue will show in the next session.

Example:
  /trekendsession .claude/projects/2026-05-01-feature/brief.md "Session 2 of 3"

Phase 1 — Resolve project directory

Resolve the nearest .claude/projects/*/brief.md from cwd (the current working directory). Use node -e enumeration (NOT shell glob — harness-mode safety):

!`node --input-type=module -e "import {existsSync, readdirSync} from 'node:fs'; import {join} from 'node:path'; const root='.claude/projects'; if(!existsSync(root)) process.exit(0); readdirSync(root).filter(d=>existsSync(join(root,d,'brief.md'))).forEach(d=>process.stdout.write(join(root,d)+'\\n'));"`

Decision tree:

• 0 candidates: print error to stderr — "no .claude/projects/<dir>/brief.md found under cwd; cannot determine project directory" — and exit 1. Do NOT fall back to a synthesized path.
• 1 candidate: use it as <project-dir>. Continue.
• >1 candidates: print all paths and ask the operator to cd into the intended project directory before retrying. Exit 1.

Phase 2 — Required args check (headless-safe)

Read $ARGUMENTS. Both <next-brief-path> and <next-label> are required. If either is missing or empty:

Error: missing required args.
Usage: /trekendsession <next-brief-path> '<next-label>'

Print to stderr and exit 1. No interactive prompt — this keeps the helper headless-safe (per brief NFR; addresses adversarial-review major #11). If you want an interactive flow, use /trekcontinue --help to see the full pipeline.

Phase 3 — Atomically write .session-state.local.json + sibling NEXT-SESSION-PROMPT.local.md

Write <project-dir>/.session-state.local.json with the schema-v1 object:

{
  "schema_version": 1,
  "project": "<project-dir>",
  "next_session_brief_path": "<arg 1>",
  "next_session_label": "<arg 2>",
  "status": "in_progress",
  "updated_at": "<now, ISO-8601>"
}

Use the atomic-write util — write to <path>.tmp, then rename into place — to avoid partial-state on crash. The util is ESM, so invoke via node --input-type=module -e with an import statement (a CommonJS shim would throw ERR_REQUIRE_ESM on Node 18+ since atomic-write.mjs is ESM).

Under node --input-type=module -e "<script>" arg1 arg2 arg3, Node sets process.argv[0] to the node binary path and user args start at process.argv[1]. Adjust the destructure if your Node version differs.

This phase ALSO writes a sibling NEXT-SESSION-PROMPT.local.md in the project directory with YAML frontmatter (produced_by: trekendsession, produced_at: <ISO-8601>, project: <project-dir>). Both files are written in a single ESM block so the writes succeed or fail together:

!`node --input-type=module -e "
import path from 'node:path';
import { writeFileSync } from 'node:fs';
import { atomicWriteJson } from './lib/util/atomic-write.mjs';
const [, dir, brief, label] = process.argv;
const now = new Date().toISOString();
const stateObj = { schema_version: 1, project: dir, next_session_brief_path: brief, next_session_label: label, status: 'in_progress', updated_at: now };
const stateFile = path.join(dir, '.session-state.local.json');
atomicWriteJson(stateFile, stateObj);
const promptFile = path.join(dir, 'NEXT-SESSION-PROMPT.local.md');
const promptBody = '---\\nproduced_by: trekendsession\\nproduced_at: ' + now + '\\nproject: ' + dir + '\\n---\\n\\n# ' + label + '\\n\\nResume via /trekcontinue.\\n';
writeFileSync(promptFile, promptBody);
console.log(stateFile);
console.log(promptFile);
" '<project-dir>' '<next-brief-path>' '<next-label>'`

Phase 4 — Validate + narrate

Validate the freshly-written state file:

!`node lib/validators/session-state-validator.mjs --json <project-dir>/.session-state.local.json`

If valid: true, print the success block matching /trekcontinue Phase 3 narration (SC-8 cross-project consistency — same template both sides):

Session state written: <project-dir>/.session-state.local.json

Project: <project-dir>
Next session: <next-label>
Brief: <next-brief-path>

In a fresh Claude session, run /trekcontinue to resume.

If valid: false, print the structured errors[] and exit 1. Investigate before retrying — usually means a bad path or label argument.

Hard rules

• Required args, no defaults. Never invent a brief path or session label. If args are missing, fail loud.
• Atomic write only. Tmp + rename — no partial state files on disk.
• Zero secrets. Status, paths, labels — never API keys, never user content beyond filenames.
• NEVER auto-invoke this command. It is operator-typed only at session-end.
• Idempotent within a session. Running twice with the same args overwrites cleanly (atomic rename); does not double-advance.