fix(issue-23-24): the dialog handler sees the ready banner on its own; only this dispatch's started is delivery evidence
Review round 1 (planner-reviewer-claude-01, reviewer-agy-01, planner-reviewer-codex-01): one blocking defect and two P2s, all confirmed. B-1. handle_startup_dialogs took its ready tokens only from the environment, which wait_for_tui_ready fills when it evaluates the adapter facts. Called on its own - as resume_session.sh calls it, with no readiness wait before it - it had no tokens, its early-return branch could never fire, and every resume of every agent idled through the full 20 s timeout (base: 0.03 s). rc was 0 throughout, so nothing failed; the resume tests just took ~30 s each. _mam_load_dialog_facts now also takes MAM_STRONG_READY_TOKENS / MAM_READY_TOKENS from the facts, but only when the caller has not set them, so a caller-set value (wait_for_tui_ready's own, or a test steering readiness) is never clobbered - the concern that made it take a single fact in the first place. S5d pins one-iteration return on a ready first frame for five adapters with no environment; S5e pins that caller tokens survive; R4 gets a wall-clock cap so a timeout-idle can no longer pass as success. The old _MAM_READY_TOKENS_CLAUDE fallback was left defined but unread - removed. R1 / N-2. delegate_wait_started treated any status past `pending` as the agent's acknowledgement. codex reproduced three false positives: `error` and `cancelled` records with no started line, and a `running` record from another dispatch. The status branch is gone; the evidence is a started line carrying this dispatch's token, which the local publisher writes before it syncs the status, so nothing that really started is missed (S7c re-pinned on the line with running/completed/error statuses; S7f/S7g pin the three negatives). N-4, taken with it: the events.log line is parsed as JSON rather than pattern- matched. publish_event nests dispatch_token under `data`, and the old regex only matched because of key order (S7h, real line shape and a reordered one). R2 / N-1. Two tests hardcoded <repo>/.venv/bin/python and failed with FileNotFoundError in every review worktree. sys.executable. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
This commit is contained in:
GodopuandClaude Fable 5.1 committed
1 parent
0dfbb2cc8a
commit
10a678c010
3 files changed
+150
-42
No files matched your search
+51
-31
@@ -71,7 +71,6 @@ done
|
||||
_MAM_MODAL_TOKENS='Do you trust the files|Yes, proceed|No, exit|Allow this|browser to authenticate|Resuming the full session|Resume from summary|Try the new fullscreen renderer\?'
|
||||
_MAM_HINT_TOKENS='Use arrow keys|Esc to cancel|Press Enter to continue'
|
||||
_MAM_DIALOG_TOKENS="${_MAM_MODAL_TOKENS}|${_MAM_HINT_TOKENS}"
|
||||
_MAM_READY_TOKENS_CLAUDE='Anthropic|Assistant|Chat|Welcome|Claude Code|Opus|Sonnet|Haiku'
|
||||
|
||||
# Workspace-relative defaults with environment overrides (Phase Z)
|
||||
HOME_DIR="${HOME_DIR:-$HOME}"
|
||||
@@ -2142,35 +2141,42 @@ delegate_publish_event() {
|
||||
# line lands in the job's events.log, which publish_event writes before its
|
||||
# wire publish so a slow broker cannot delay the verdict.
|
||||
#
|
||||
# Returns 0 on that evidence, 1 if neither appeared within T. Never re-injects:
|
||||
# the single-injection contract is fail-closed.
|
||||
# Returns 0 on that evidence, 1 if it did not appear within T. Never
|
||||
# re-injects: the single-injection contract is fail-closed.
|
||||
#
|
||||
# The evidence is a `started` line in the job's events.log carrying THIS
|
||||
# dispatch's token (nested under `data`, as publish_event writes it; the line
|
||||
# is parsed as JSON, not pattern-matched, so key order is irrelevant). The
|
||||
# registry's status is deliberately NOT evidence: a record can leave `pending`
|
||||
# because another writer closed it (`error`, `cancelled`) or because a
|
||||
# different dispatch is `running`, none of which says this agent saw this
|
||||
# prompt (review R1). The local publisher writes the log line before it syncs
|
||||
# the status, so nothing that really started is missed.
|
||||
delegate_wait_started() {
|
||||
local job_id="$1" ack_s="${2:-180}" tok="${3:-}"
|
||||
[ -n "$job_id" ] || return 1
|
||||
local reg_dir="${MAM_JOBS_DIR:-${WORKSPACE_ROOT:-$PWD}/.mam/jobs}"
|
||||
local rec="$reg_dir/$job_id.json"
|
||||
local ev_log="$reg_dir/$job_id.events.log"
|
||||
local started_re='"event": *"started"'
|
||||
if [ -n "$tok" ]; then
|
||||
started_re='"event": *"started".*"dispatch_token": *"'"$tok"'"'
|
||||
fi
|
||||
local deadline st
|
||||
local deadline
|
||||
deadline=$(( $(date +%s) + ack_s ))
|
||||
while :; do
|
||||
st=""
|
||||
if [ -f "$rec" ]; then
|
||||
st=$(REC="$rec" python3 -c "
|
||||
import json, os
|
||||
try:
|
||||
print(json.load(open(os.environ['REC'])).get('status', '') or '')
|
||||
except Exception:
|
||||
print('')
|
||||
" 2>/dev/null || true)
|
||||
fi
|
||||
if [ -n "$st" ] && [ "$st" != "pending" ]; then
|
||||
return 0
|
||||
fi
|
||||
if [ -f "$ev_log" ] && grep -Eq "$started_re" "$ev_log" 2>/dev/null; then
|
||||
if [ -f "$ev_log" ] && EV_LOG="$ev_log" EV_TOK="$tok" python3 -c '
|
||||
import json, os, sys
|
||||
tok = os.environ.get("EV_TOK", "")
|
||||
with open(os.environ["EV_LOG"], encoding="utf-8", errors="replace") as f:
|
||||
for line in f:
|
||||
try:
|
||||
e = json.loads(line)
|
||||
except Exception:
|
||||
continue
|
||||
if not isinstance(e, dict) or e.get("event") != "started":
|
||||
continue
|
||||
data = e.get("data") if isinstance(e.get("data"), dict) else {}
|
||||
seen = data.get("dispatch_token") or e.get("dispatch_token") or ""
|
||||
if not tok or seen == tok:
|
||||
sys.exit(0)
|
||||
sys.exit(1)
|
||||
' 2>/dev/null; then
|
||||
return 0
|
||||
fi
|
||||
if [ "$(date +%s)" -ge "$deadline" ]; then
|
||||
@@ -2752,21 +2758,35 @@ send_keys_safe() {
|
||||
}
|
||||
|
||||
# _mam_load_dialog_facts <agent>
|
||||
# Populate MAM_STARTUP_DIALOGS for <agent>, once per agent per shell. Only that
|
||||
# one fact is taken: `facts` is an eval contract (F8), and evaluating all of it
|
||||
# here would clobber ready/placeholder tokens a caller deliberately set.
|
||||
# An agent the adapters do not know keeps an empty list.
|
||||
# Populate MAM_STARTUP_DIALOGS for <agent>, once per agent per shell, and the
|
||||
# ready tokens (MAM_STRONG_READY_TOKENS / MAM_READY_TOKENS) only when the caller
|
||||
# has not set them. `facts` is an eval contract (F8); evaluating all of it here
|
||||
# would clobber tokens a caller deliberately set, so only these are taken, and
|
||||
# the tokens only fill a gap. Without them the handler could never recognise a
|
||||
# ready screen when called on its own - resume_session.sh does exactly that,
|
||||
# with no wait_for_tui_ready before it - and idled through its whole timeout on
|
||||
# every resume (review B-1). An agent the adapters do not know keeps an empty
|
||||
# list and no tokens.
|
||||
_mam_load_dialog_facts() {
|
||||
local agent="$1" _f=""
|
||||
local agent="$1" _f="" _d="" _s="" _r=""
|
||||
if [ "${_MAM_DIALOGS_AGENT:-}" = "$agent" ]; then
|
||||
return 0
|
||||
fi
|
||||
_f="$("$(_delegate_py_bin)" -m lib_py.agents facts "$agent" 2>/dev/null | sed -n 's/^MAM_STARTUP_DIALOGS=//p')" || _f=""
|
||||
if [ -n "$_f" ]; then
|
||||
eval "MAM_STARTUP_DIALOGS=$_f"
|
||||
_f="$("$(_delegate_py_bin)" -m lib_py.agents facts "$agent" 2>/dev/null)" || _f=""
|
||||
_d="$(printf '%s\n' "$_f" | sed -n 's/^MAM_STARTUP_DIALOGS=//p')"
|
||||
_s="$(printf '%s\n' "$_f" | sed -n 's/^MAM_STRONG_READY_TOKENS=//p')"
|
||||
_r="$(printf '%s\n' "$_f" | sed -n 's/^MAM_READY_TOKENS=//p')"
|
||||
if [ -n "$_d" ]; then
|
||||
eval "MAM_STARTUP_DIALOGS=$_d"
|
||||
else
|
||||
MAM_STARTUP_DIALOGS='[]'
|
||||
fi
|
||||
if [ -z "${MAM_STRONG_READY_TOKENS:-}" ] && [ -n "$_s" ]; then
|
||||
eval "MAM_STRONG_READY_TOKENS=$_s"
|
||||
fi
|
||||
if [ -z "${MAM_READY_TOKENS:-}" ] && [ -n "$_r" ]; then
|
||||
eval "MAM_READY_TOKENS=$_r"
|
||||
fi
|
||||
_MAM_DIALOGS_AGENT="$agent"
|
||||
return 0
|
||||
}
|
||||
|
||||
Reference in new issue
Block a user