d5c2c213a3
Fixes #261 ## Changes Fixed gardener hanging forever when Claude skips phase protocol. Three changes: (1) gardener-agent.sh: replaced 999999s timeout with 7200s (2h, matching dev-agent); (2) lib/agent-session.sh: added idle-prompt detection to monitor_phase_loop — if Claude returns to the ❯ prompt for 3 consecutive polls with no phase file written, exits immediately with _MONITOR_LOOP_EXIT=idle_prompt (only fires when phase file is empty, so awaiting_ci/review waits are unaffected); (3) gardener prompt: removed 'no time limit' wording, replaced with explicit phase-write requirement. Co-authored-by: openhands <openhands@all-hands.dev> Reviewed-on: https://codeberg.org/johba/disinto/pulls/263 Reviewed-by: Disinto_bot <disinto_bot@noreply.codeberg.org>
195 lines
7 KiB
Bash
195 lines
7 KiB
Bash
#!/usr/bin/env bash
|
||
# agent-session.sh — Shared tmux + Claude interactive session helpers
|
||
#
|
||
# Source this into agent orchestrator scripts for reusable session management.
|
||
#
|
||
# Functions:
|
||
# agent_wait_for_claude_ready SESSION_NAME [TIMEOUT_SECS]
|
||
# agent_inject_into_session SESSION_NAME TEXT
|
||
# agent_kill_session SESSION_NAME
|
||
# monitor_phase_loop PHASE_FILE IDLE_TIMEOUT_SECS CALLBACK_FN [SESSION_NAME]
|
||
|
||
# Wait for the Claude ❯ ready prompt in a tmux pane.
|
||
# Returns 0 if ready within TIMEOUT_SECS (default 120), 1 otherwise.
|
||
agent_wait_for_claude_ready() {
|
||
local session="$1"
|
||
local timeout="${2:-120}"
|
||
local elapsed=0
|
||
while [ "$elapsed" -lt "$timeout" ]; do
|
||
if tmux capture-pane -t "$session" -p 2>/dev/null | grep -q '❯'; then
|
||
return 0
|
||
fi
|
||
sleep 2
|
||
elapsed=$((elapsed + 2))
|
||
done
|
||
return 1
|
||
}
|
||
|
||
# Paste TEXT into SESSION (waits for Claude to be ready first), then press Enter.
|
||
agent_inject_into_session() {
|
||
local session="$1"
|
||
local text="$2"
|
||
local tmpfile
|
||
agent_wait_for_claude_ready "$session" 120 || true
|
||
tmpfile=$(mktemp /tmp/agent-inject-XXXXXX)
|
||
printf '%s' "$text" > "$tmpfile"
|
||
tmux load-buffer -b "agent-inject-$$" "$tmpfile"
|
||
tmux paste-buffer -t "$session" -b "agent-inject-$$"
|
||
sleep 0.5
|
||
tmux send-keys -t "$session" "" Enter
|
||
tmux delete-buffer -b "agent-inject-$$" 2>/dev/null || true
|
||
rm -f "$tmpfile"
|
||
}
|
||
|
||
# Create a tmux session running Claude in the given workdir.
|
||
# Returns 0 if session is ready, 1 otherwise.
|
||
create_agent_session() {
|
||
local session="$1"
|
||
local workdir="${2:-.}"
|
||
tmux new-session -d -s "$session" -c "$workdir" \
|
||
"claude --dangerously-skip-permissions" 2>/dev/null
|
||
sleep 1
|
||
tmux has-session -t "$session" 2>/dev/null || return 1
|
||
agent_wait_for_claude_ready "$session" 120 || return 1
|
||
return 0
|
||
}
|
||
|
||
# Inject a prompt/formula into a session (alias for agent_inject_into_session).
|
||
inject_formula() {
|
||
agent_inject_into_session "$@"
|
||
}
|
||
|
||
# Monitor a phase file, calling a callback on changes and handling idle timeout.
|
||
# Sets _MONITOR_LOOP_EXIT to the exit reason (idle_timeout, idle_prompt, done, failed, break).
|
||
# Sets _MONITOR_SESSION to the resolved session name (arg 4 or $SESSION_NAME).
|
||
# Callbacks should reference _MONITOR_SESSION instead of $SESSION_NAME directly.
|
||
# Args: phase_file idle_timeout_secs callback_fn [session_name]
|
||
# session_name — tmux session to health-check; falls back to $SESSION_NAME global
|
||
#
|
||
# Idle prompt detection: if Claude returns to the ❯ prompt for 3 consecutive polls
|
||
# WITHOUT having written any phase signal, the session is killed and the callback is
|
||
# invoked with "PHASE:failed". This handles the case where Claude completes its work
|
||
# but skips the phase protocol entirely.
|
||
monitor_phase_loop() {
|
||
local phase_file="$1"
|
||
local idle_timeout="$2"
|
||
local callback="$3"
|
||
local _session="${4:-${SESSION_NAME:-}}"
|
||
# Export resolved session name so callbacks can reference it regardless of
|
||
# which session was passed to monitor_phase_loop (analogous to _MONITOR_LOOP_EXIT).
|
||
export _MONITOR_SESSION="$_session"
|
||
local poll_interval="${PHASE_POLL_INTERVAL:-10}"
|
||
local last_mtime=0
|
||
local idle_elapsed=0
|
||
local idle_pane_count=0
|
||
|
||
while true; do
|
||
sleep "$poll_interval"
|
||
idle_elapsed=$(( idle_elapsed + poll_interval ))
|
||
|
||
# Session health check
|
||
if ! tmux has-session -t "${_session}" 2>/dev/null; then
|
||
local current_phase
|
||
current_phase=$(head -1 "$phase_file" 2>/dev/null | tr -d '[:space:]' || true)
|
||
case "$current_phase" in
|
||
PHASE:done|PHASE:failed|PHASE:merged)
|
||
;; # terminal — fall through to phase handler
|
||
*)
|
||
# Call callback with "crashed" — let agent-specific code handle recovery
|
||
if type "${callback}" &>/dev/null; then
|
||
"$callback" "PHASE:crashed"
|
||
fi
|
||
# If callback didn't restart session, break
|
||
if ! tmux has-session -t "${_session}" 2>/dev/null; then
|
||
_MONITOR_LOOP_EXIT="crashed"
|
||
return 1
|
||
fi
|
||
idle_elapsed=0
|
||
idle_pane_count=0
|
||
continue
|
||
;;
|
||
esac
|
||
fi
|
||
|
||
# Check phase file for changes
|
||
local phase_mtime
|
||
phase_mtime=$(stat -c %Y "$phase_file" 2>/dev/null || echo 0)
|
||
local current_phase
|
||
current_phase=$(head -1 "$phase_file" 2>/dev/null | tr -d '[:space:]' || true)
|
||
|
||
if [ -z "$current_phase" ] || [ "$phase_mtime" -le "$last_mtime" ]; then
|
||
# No phase change — check idle timeout
|
||
if [ "$idle_elapsed" -ge "$idle_timeout" ]; then
|
||
_MONITOR_LOOP_EXIT="idle_timeout"
|
||
agent_kill_session "${_session}"
|
||
return 0
|
||
fi
|
||
# Idle prompt detection: Claude finished without writing a phase signal.
|
||
# Only fires when current_phase is empty (no phase ever written).
|
||
# Note: tmux capture-pane captures the full visible pane area, not just the
|
||
# last line. Prior tool output containing ❯ (e.g. a zsh subshell prompt in
|
||
# Claude's output) could trigger a false positive — the same risk exists in
|
||
# agent_wait_for_claude_ready(). Requiring 3 consecutive polls (≥2 poll
|
||
# intervals of sustained idle) reduces but does not eliminate this risk.
|
||
if [ -z "$current_phase" ] && tmux has-session -t "${_session}" 2>/dev/null && \
|
||
tmux capture-pane -t "${_session}" -p 2>/dev/null | grep -q '❯'; then
|
||
idle_pane_count=$(( idle_pane_count + 1 ))
|
||
if [ "$idle_pane_count" -ge 3 ]; then
|
||
_MONITOR_LOOP_EXIT="idle_prompt"
|
||
# Session is already killed before the callback is invoked.
|
||
# Callbacks that handle PHASE:failed must not assume the session is alive.
|
||
agent_kill_session "${_session}"
|
||
if type "${callback}" &>/dev/null; then
|
||
"$callback" "PHASE:failed"
|
||
fi
|
||
return 0
|
||
fi
|
||
else
|
||
idle_pane_count=0
|
||
fi
|
||
continue
|
||
fi
|
||
|
||
# Phase changed
|
||
last_mtime="$phase_mtime"
|
||
# shellcheck disable=SC2034 # read by phase-handler.sh callback
|
||
LAST_PHASE_MTIME="$phase_mtime"
|
||
idle_elapsed=0
|
||
|
||
# Terminal phases
|
||
case "$current_phase" in
|
||
PHASE:done|PHASE:merged)
|
||
_MONITOR_LOOP_EXIT="done"
|
||
if type "${callback}" &>/dev/null; then
|
||
"$callback" "$current_phase"
|
||
fi
|
||
return 0
|
||
;;
|
||
PHASE:failed|PHASE:needs_human)
|
||
_MONITOR_LOOP_EXIT="$current_phase"
|
||
if type "${callback}" &>/dev/null; then
|
||
"$callback" "$current_phase"
|
||
fi
|
||
return 0
|
||
;;
|
||
esac
|
||
|
||
# Non-terminal phase — call callback
|
||
if type "${callback}" &>/dev/null; then
|
||
"$callback" "$current_phase"
|
||
fi
|
||
done
|
||
}
|
||
|
||
# Kill a tmux session gracefully (no-op if not found).
|
||
agent_kill_session() {
|
||
local session="${1:-}"
|
||
[ -n "$session" ] && tmux kill-session -t "$session" 2>/dev/null || true
|
||
}
|
||
|
||
# Read the current phase from a phase file, stripped of whitespace.
|
||
# Usage: read_phase [file] — defaults to $PHASE_FILE
|
||
read_phase() {
|
||
local file="${1:-${PHASE_FILE:-}}"
|
||
{ cat "$file" 2>/dev/null || true; } | head -1 | tr -d '[:space:]'
|
||
}
|