Test self-hosted environments end to end

{
  "hooks": {
    "Stop": [
      {
        "hooks": [
          {
            "type": "command",
            "timeout": 10,
            "command": "\"$CLAUDE_CONFIG_DIR/hooks/e2e-stop-hook-capture.sh\""
          }
        ]
      }
    ]
  }
}

#!/bin/sh
# Stop hook for testing a self-hosted environment end to end: writes each
# turn's final assistant reply to $E2E_REPLY_DIR/<session_id>.txt so a
# co-located test driver can read it without calling the Anthropic API.
# Install on the TEST runner only. Requires jq.

# No-op unless the driver is listening. Never fail the turn.
[ -n "${E2E_REPLY_DIR:-}" ] && [ -d "$E2E_REPLY_DIR" ] || exit 0

# CLAUDE_CODE_REMOTE_SESSION_ID is exported in cse_... form; the session
# id the dispatch CLI prints is in session_... form. Same id, different
# prefix.
sid=$(printf '%s' "${CLAUDE_CODE_REMOTE_SESSION_ID:-}" | sed 's/^cse_/session_/')
[ -n "$sid" ] || exit 0

# last_assistant_message is absent when the final assistant turn had no
# text, such as a tool-use-only turn. The `// empty` filter makes that a
# zero-byte write rather than the literal string "null".
jq -r '.last_assistant_message // empty' >> "$E2E_REPLY_DIR/$sid.txt" 2>/dev/null
exit 0

#!/usr/bin/env bash
# End-to-end test against a self-hosted environment, using Stop-hook read-back.
# Prereqs: `claude auth login` has been run on this machine (see "Authenticate
# from CI" below); jq is installed; CLAUDE_TEST_ENVIRONMENT_ID names an
# environment whose runner is the one on this host, with the capture hook
# installed and E2E_REPLY_DIR in its environment.

set -euo pipefail

: "${CLAUDE_TEST_ENVIRONMENT_ID:=${CLAUDE_TEST_POOL_ID:-}}"  # CLAUDE_TEST_POOL_ID is the legacy spelling
: "${CLAUDE_TEST_ENVIRONMENT_ID:?set CLAUDE_TEST_ENVIRONMENT_ID to a ccpool_... id served by a runner on this host}"
: "${E2E_REPLY_DIR:?set E2E_REPLY_DIR to the directory the Stop hook on your test runner writes to, and export it to the runner process}"
: "${TEST_REPO_REF:=main}"

[ -d "$E2E_REPLY_DIR" ] || {
  echo "FAIL: E2E_REPLY_DIR ($E2E_REPLY_DIR) does not exist. The Stop hook on the runner needs it." >&2
  exit 1
}

# Waits until $E2E_REPLY_DIR/<session_id>.txt contains $2, or fails after
# 90 seconds. Tune the timeout to your environment's cold-start time. The
# file is written by the Stop hook on the runner.
await_reply() {
  local expect="$2" f="$E2E_REPLY_DIR/$1.txt"
  local deadline=$(($(date +%s) + 90))
  while :; do
    if [ -f "$f" ] && grep -qF -- "$expect" "$f"; then
      return
    fi
    [ "$(date +%s)" -lt "$deadline" ] || {
      echo "FAIL: '$expect' not in $f within 90s. The Stop hook on the runner did not write it." >&2
      echo "-- $E2E_REPLY_DIR contents --" >&2; ls -la "$E2E_REPLY_DIR" >&2
      [ -f "$f" ] && { echo "-- $f --" >&2; cat "$f" >&2; }
      exit 1
    }
    sleep 1
  done
}

# 1. Create the session on the test environment. Run from a git checkout
# so the CLI can auto-detect the repo. --ref pins the checkout to a named
# ref regardless of local HEAD.
TURN1="e2e-probe-$(date +%s)-$$: say exactly 'ok: custom tools are reachable' and nothing else"
EXPECT1="ok: custom tools are reachable"
create_json=$(claude -p "$TURN1" --environment "$CLAUDE_TEST_ENVIRONMENT_ID" \
  --ref "$TEST_REPO_REF" --output-format json)
echo "create: $create_json"
SESSION_ID=$(jq -er '.session_id' <<<"$create_json")

# 2. Wait for the turn-1 reply.
await_reply "$SESSION_ID" "$EXPECT1"
echo "turn-1 reply ok"

# 3. Post a follow-up via the CLI.
TURN2="e2e-probe-followup-$(date +%s): say exactly 'ok: follow-up delivered' and nothing else"
EXPECT2="ok: follow-up delivered"
followup_json=$(claude -p "$TURN2" --cloud "$SESSION_ID" --output-format json)
echo "followup: $followup_json"
jq -e '.ok == true' <<<"$followup_json" >/dev/null

# 4. Wait for the turn-2 reply.
await_reply "$SESSION_ID" "$EXPECT2"
echo "turn-2 reply ok"

echo "PASS: test-environment round-trip (session $SESSION_ID)"

#!/bin/sh
# Variant of the capture hook for runners on separate infrastructure.
# Set E2E_REPLY_URL on the runner to an endpoint the driver controls.
[ -n "${E2E_REPLY_URL:-}" ] || exit 0
sid=$(printf '%s' "${CLAUDE_CODE_REMOTE_SESSION_ID:-}" | sed 's/^cse_/session_/')
[ -n "$sid" ] || exit 0
jq -r '.last_assistant_message // empty' | \
  curl -fsS -X POST --data-binary @- "$E2E_REPLY_URL/$sid" >/dev/null 2>&1
exit 0

create=$(curl -fsS -X POST -H @- \
  -H "anthropic-beta: ccr-byoc-2025-07-29" -H "anthropic-version: 2023-06-01" \
  -H "content-type: application/json" \
  -d '{"name":"ci-test-environment"}' \
  https://api.anthropic.com/v1/code/runners/self-hosted/pools \
  <<<"Authorization: Bearer $ADMIN_TOKEN")
ENVIRONMENT_ID=$(jq -er .pool.pool_id <<<"$create")
ENVIRONMENT_SECRET=$(jq -er .pool_secret <<<"$create")

curl -fsS -X DELETE -H @- \
  -H "anthropic-beta: ccr-byoc-2025-07-29" -H "anthropic-version: 2023-06-01" \
  "https://api.anthropic.com/v1/code/runners/self-hosted/pools/$ENVIRONMENT_ID" \
  <<<"Authorization: Bearer $ADMIN_TOKEN"