Merge-workspace review: round 1 (@518beda) claude agy grok PASS, codex
NOT PASS (finalize wait measured on the wall clock); fixed in 4c86107.
Round 2 delta (@4c86107) claude agy grok PASS; codex (24b21b9c, after
817d1650 closed deadline_timeout with no report) found R1 closed and no
new defect, but withheld PASS only because its sandbox could not bind
the suite's loopback broker. The same two-file suite run here at
4c86107: 278 passed. Full suite at 518beda on macOS / Python 3.9:
1711 passed / 1 failed / 38 skipped; the failure
(test_issue45_restore, herdr 0.9.3 cwd restore) also fails on main.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VCgu9Fa9iT7TbJUSzdq4Ff
codex, PR #51 round 1. wrapper._sleep computed the span and the remainder
with time.time(). The broker re-observation (up to 3 s) and the disk-heartbeat
grace (1 s) use it, so a wall clock stepped back during the wait stretched it
by the step: on a mocked clock stepped back 10 s, an already completed job was
seen after 11 s / 13 s instead of 1 s / 3 s. The old bash ran `sleep 1` /
`sleep "$left"`, which do not follow the wall clock.
_sleep now measures on time.monotonic(). The deadline (START_TIME + TIMEOUT),
the evidence window and event timestamps stay on the wall clock (_now), as in
the bash.
test_u_a_wait_is_not_stretched_by_a_wall_clock_step_back (1 s, 3 s) swaps the
module's time for a clock stepped back 10 s during the first sleep; on the
previous code it measures 11.0 / 13.0 and fails. The comparison test and the
finalize-related behaviour tests (issue33, issue18, issue14) on macOS /
Python 3.9: 321 passed.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VCgu9Fa9iT7TbJUSzdq4Ff
kill(pid, 0) succeeds for a zombie. A caller that captures the wrapper's
output and calls communicate() after TERM leaves the wrapper unreaped while
the finalizer holds its pipes, so the owner check passed until the deadline
and the job was still closed (codex, round 2; reproduced with the real
registry). _alive now asks `ps -o stat=` (POSIX, no /proc) once kill(0)
succeeds and treats state Z as gone, as tests/conftest.py::_pid_alive does;
no ps answer keeps kill(0)'s verdict. The owner is looked at every 0.5 s.
Tests: TERM + communicate() with no wait() for both graces (stand-ins) and
for the timeout grace with the real registry, old vs new; a zombie is not
alive. All four fail on c5cebe6.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
finalize-end ran the disk grace and the broker re-observation as a child
of the wrapper; TERM to the wrapper left it running, and at the deadline it
still closed the job and published the error (codex R1, reproduced with the
real registry). The bash loops it replaced ended with the wrapper.
The wrapper now passes its own pid (--watch-pid "$$", as for the stall
watcher). finalize-end checks it every 0.2 s through both waits and before
the close and the event, and leaves without either once it is gone.
A comparison test sends TERM to the old and the new wrapper inside each
grace: both exit at once, leave no process behind and make no call.
Also: no blank line at the end of the old-decisions fixture, and the #42
inventory follows main() one line down.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The wrapper keeps spawn / wait / kill, key injection and the herdr
diagnostic probe; what it decided in bash is now lib_py/delegation/wrapper.py,
reached through one `_decide` helper:
- finalize_unfinished: the clock choice, the disk grace and broker
re-observation, the close request / label, the close and the event
(finalize-begin / finalize-end; bash runs only the busy probe between them)
- start_stall_watch: whether to watch (MAM_STALL_WATCH, remote, human)
- _map_sub_rc, _rc_for (+ MAM_DELEGATE_FAIL_CLOSED), the subscriber
early-exit check and cmd_wait's rc normalisation
- mam_int / mam_int_knob run lib_py/ints.py, which is also the runner's
_positive_int: one implementation of the Issue #26 rule
No behaviour change: tests/test_issue17_item4_decisions.py runs the old
bash functions (copied verbatim from 7209750) and the new wrapper on the
same inputs and compares output, FINAL_JOB_STATUS and the registry /
publish calls. Three static tests that pinned the old bash literals now
pin the Python entry points instead.
Refs #17
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
PR #48 already carries the 4.8.5 lockstep bump. Merge-workspace review:
round 1 (@35935f9) claude agy grok NOT PASS (test portability: tomllib on
Python 3.9, /proc and /tmp on macOS), codex no verdict (model at capacity,
budget spent); fixed in 36f0b8d and e8d9151. Round 2 (@e8d9151) codex NOT
PASS (unrunnable config check passed an unchecked merge, odd pids closed a
pane, nan dropped the user's settings); fixed in ab93776. Round 3
(@ab93776) 4/4 PASS. Full suite at ab93776 on macOS / Python 3.9: 1456
passed / 0 failed / 38 skipped. Reports and the round-3 identity sidecars
go to .agents/reports/<session>/.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VCgu9Fa9iT7TbJUSzdq4Ff
codex round 2 (PR #48).
- R1: when `herdr config check` could not run (timeout, OSError), the
merged config was handed to the server as checked. A merge with a schema
error makes herdr drop the whole file, restore back on - the #45 failure.
The merged body is no longer used unchecked: _write_checked falls to the
fixed MINIMAL config with a warning. When the check cannot run on MINIMAL
either, MINIMAL is still used (with its own warning) rather than no
config: returning none would leave restore on, and MINIMAL is a fixed
two-line file the real-herdr test accepts. Unknown non-zero exits stay as
they were - herdr exits non-zero for harmless warnings (an unknown
section) that do not drop the file.
- R2: _shell_in_foreground compared shell_pid and the foreground group with
==, so 0/0, False/False, ""/"" or -1/-1 closed the pane. Both must now be
positive ints (bool excluded) before they are compared.
- R3: the re-parse check used ==, and nan != nan, so a valid TOML nan threw
away every other user setting even on Python 3.11. _same_doc compares
documents recursively with nan equal to nan.
Tests: R1 (timeout, OSError) and R3 (top-level, array, nested nan) in
test_issue45_herdr_config.py; R2 in the new tests/test_issue45_restore_unit.py
(a herdr stub: zero, false, empty, negative, null, string, true, float;
missing info; a real shell closed; a busy pane kept). On the previous code
12 of them fail. Python 3.11: 67 passed; Python 3.9: 33 passed / 34 skipped
(tomllib-only). Real-herdr restore tests and related files on 3.9: 197
passed / 1 skipped.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VCgu9Fa9iT7TbJUSzdq4Ff
tests/test_issue45_herdr_config.py imported tomllib at module level. On
Python 3.9 - macOS's /usr/bin/python3, which the venvs and the bootstrap's
python3 use here - the import failed during collection and pytest ran no
test of the whole suite.
The import is optional now, and the 29 tests that parse a result with
tomllib or expect the user's settings kept are marked needs_tomllib: on
Python < 3.11 herdr_config deliberately writes the key-only config (restore
still off, the other settings dropped, a warning on stderr), which
test_without_tomllib_restore_is_still_off covers on every Python.
Python 3.9: 22 passed / 29 skipped; Python 3.11: 51 passed.
create SKILL.md (same line, so the #42 inventory is unchanged) and the
4.8.5 entry state that building the server config needs tomllib (Python
3.11+) in the python3 on PATH, and what an older python3 loses. Checked
with Python 3.9 in a throwaway HOME: the warning reaches stderr (the
bootstrap captures only stdout) and the user's file is untouched.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VCgu9Fa9iT7TbJUSzdq4Ff
The fallback wrote <.mam>/herdr-server-config.toml unchecked, so it could
replace a foreign file there, the source itself, or a link to it. It now goes
through output_path like the normal path (source identity incl. aliases,
generated-for-this-source ownership, then a per-source name) and writes
nothing when no name is safe.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
R1: tomllib accepting a file is not herdr accepting it (a schema error makes
herdr drop the whole file, restore included). The shim passes REAL_HERDR and
the written file must pass `herdr config check` ("parse error"/"using defaults"
reject; unknown keys and sound-file notices do not), else the key-only file is
written and checked. A non-table `session` and a source that is not UTF-8 reach
that fallback instead of raising.
R2: the line edit is replaced by parse -> set -> serialize; the result must
parse back to the source plus the key, so dotted keys and inline tables keep
the user's other settings.
R3: the output is never the source (aliases included) nor a file not generated
for the same source; then a per-source name beside it.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Issue #45 A+B: MAM's isolated herdr servers start with restore-on-restart off,
and resume closes the session's own restored empty shell. Not reviewed yet.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The shim runs a bare python3. Before 3.11 the module failed to import and the
server started with restore on; now it gets the key alone, with a warning.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
After a restart with restore off, the session's saved pane comes back as an
empty shell (in $HOME when its directory is gone) holding the agent_session it
reported. A resume with a CP_PREFIX cannot reuse it, so it stayed next to the
new pane. Just before spawning, resume closes panes whose agent_session is the
id being resumed, with no live agent and only the shell in the foreground; the
registry is not consulted, since a session whose server died stays running.
tests/test_issue45_restore.py drives a real herdr server under a throwaway HOME
and session with a fake claude: restore stays off through the MAM bootstrap
(with a restore-on control), the close conditions, and create -> crash ->
resume leaving one pane.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The headless bootstrap regenerates the server config on every start and hands
it to the server as HERDR_CONFIG_PATH. Without a file the server still starts,
with a warning. mam_sandbox unsets HERDR_CONFIG_PATH/XDG_CONFIG_HOME so the
file lands in the sandbox HOME.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
lib_py/herdr_config.py builds the user's herdr config (HERDR_CONFIG_PATH, else
XDG_CONFIG_HOME, else ~/.config, as herdr reads it) with only
[session] resume_agents_on_restore forced to false, written next to the source
so relative paths resolve the same. The text merge is re-parsed; a merge that
does not leave the rest equal falls back to the key alone, since herdr drops a
config that does not parse and would restore again.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The .claude/skills check accepts both local layouts and fails on a dangling
link. Review: round 1 (@e1ed270) claude agy grok PASS, codex NOT PASS (a
dangling top-level link was skipped); fixed in 150b493; round 2 4/4 PASS.
Reports and the round-2 identity sidecars go to .agents/reports/<session>/.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VCgu9Fa9iT7TbJUSzdq4Ff
Issue #42 stages 1-2: the SKILL.md code-block inventory as test data and
the removal of blocks the entry scripts already do. Merge-workspace review:
round 1 (@8d26106) claude agy grok PASS, codex NOT PASS (R1-R3); fixed in
17eba09 (docs, inventory data and the guard test only); round 2 4/4 PASS.
Full suite at 8d26106 1408 passed / 0 failed. Reports and the round-2
identity sidecars go to .agents/reports/<session>/.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VCgu9Fa9iT7TbJUSzdq4Ff
Merge-workspace review of PR #46 (codex R1-R3 and C1, claude O1 and O4).
- R1: resume never attaches, and the server it exports does not reach the
calling shell; the native herdr binary does not route on environment
variables. The attach advice and the Verification block now name the
server: `herdr --session <server> agent attach <name>`, with <server> the
row's herdr_session.
- R2: --dry-run in resume and create skips the spawn and the registry
update, but the checks before it still run and on macOS remove the
quarantine attribute from the agent binary. The option rows say so.
- R3: test_no_deleted_body_came_back compares every current block with the
deleted bodies by exact sha and by a whitespace-insensitive fingerprint
(stored as base_fingerprint), independently of the inventory, so a
deleted block cannot return by being listed again under class c.
Replaying the review's probe (the deleted resume Workflow re-added and
inventoried as c) fails the new test and passes the old one.
- C1 / O1: the base create call block at 263-266 (class c) folded into the
Workflow call is recorded under "superseded"; the 37 base blocks are all
accounted for.
- O4: create exit 42 also covers MAM_KILL_ON_READY_TIMEOUT=1; stop's no-op
exit 0 does not apply with --purge-conversation.
- The inventory's positions and shas are regenerated for the edited blocks;
every classification is unchanged.
No product code changed.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VCgu9Fa9iT7TbJUSzdq4Ff
The registry update after the kill chain raises SystemExit(1) when the row
disappeared during the run (stop_session.sh:310), so "exit 1 changed nothing"
was false on that path. The stop table now says so, the code is declared as a
passthrough, and the test requires every integer SystemExit in an entry
script's heredocs to be declared - the check that would have caught it.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Stage 1: tests/data/skill_code_blocks.json lists all 37 fenced blocks of the
eight SKILL.md files at base 45d1621 (indented fences count), classed (a)
duplicate of a script, (b) procedure no script offers, (c) example/call/
diagram, with script file:line evidence and recorded mismatches.
tests/test_issue42_skill_blocks.py fails when a block changes without the
inventory, an (a) block comes back, a removed block's entry call is missing,
an exit-code table drifts from the script, or evidence points nowhere.
Stage 2: the five (a) blocks are gone - resume Workflow, stop pre-flight,
create pre-flight / Workflow / manual YAML append - replaced by the
entry-point call with option and exit-code tables. Each exit table has a
catch-all row: under set -e a failing sub-step's code passes through.
create's exit 4 is real (the YAML write raises SystemExit(4) for a duplicate
running row) and is listed as such. Doc-to-script mismatches are fixed in the
doc (resume Case 3 / no attach, stop --purge-conversation --yes, status
--json keys, create cmd_full and the nonexistent yaml-edit script). No
behaviour change, no version bump.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
PR #41/#43 review follow-ups F1-F6, implemented by creator-claude-01 in a
loop and reviewed by claude, agy, grok and codex: round 1 (@95eabc6)
codex NOT PASS (a failed env load cached as loaded), fixed in 75f364e;
round 2 4/4 PASS. Full suite at 75f364e 1380 passed / 0 failed. Reviewer
reports (round 2 with identity sidecars) and the creator's reports go to
.agents/reports/<session>/.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VCgu9Fa9iT7TbJUSzdq4Ff
ensure_env_loaded() set _env_loaded before _load_dotenv() ran. With F2,
load_env_or_report() turns the EnvFileError into a return value, so a second
main() in the same process skipped the unreadable file and ran unconfigured
(codex R1: registry.main twice -> rc 1 then rc 0 with a job registered; a
repaired file was never read). The flag is now set only after a successful
load: a failure is retried on the next call, a success still loads once.
envfile parses the whole file before applying, so a failed load sets nothing.
MESSAGING.md: the one-line ERROR is the Python entry points'; the wrapper
adds its own "ERROR: cannot load <path>" line (codex, minor).
Test: in one process, registry.main twice on an undecodable file is rc 1
both times, prints the ERROR line twice and registers nothing; the repaired
file is applied on the next call; a later change is not re-read. At 95eabc6
it fails with rc [1, 0], one job registered and the value unset.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HCGpJXhSZasJLU38ksDghe
5edf913 gave job_subscriber.main a bare `return 1`; its exit codes are
returned by name (test_issue5 test_job_subscriber_cli_contract_snapshot).
The value stays 1 - what the EnvFileError traceback exited with before -
and is RC_ERROR. The wrapper reads the same file first and exits 1 itself,
so it never starts a subscriber that would report this.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HCGpJXhSZasJLU38ksDghe
delegate-job SKILL.md said a watcher outlives a killed wrapper by "one
wait, <= 60 s". That bound is the herdr wait's; a wrapper that goes while a
notice is being published is noticed when that publish ends. The text now
says both (PR #41 codex round 3).
"a wrapper gone during the wait" switched alive() by call count, so the
watcher saw the wrapper gone at the next loop head and never entered the
second wait (ticks == [1] with that band). The wrapper now vanishes inside
the second herdr wait (_during_notice's in_wait hook), and the test checks
that the second wait happened and that alive() was true until then. The
same test fails when the post-wait _wrapper_gone() check is removed.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HCGpJXhSZasJLU38ksDghe
stall_watch read MAM_TEST_UNRELIABLE_AGENT to pretend an adapter's
agent_status was unreliable (PR #41 M7). The branch is gone. S13 now runs
the real stall_watch.main() in a process where the adapter itself reports
agent_status_reliable = False (_UNRELIABLE_MAIN), and checks the same
things as before: no idle notice or nudge, the blocked notice, and the
"idle judgement off" log line. A static check keeps MAM_TEST_ out of the
watcher (fails at 0051fd6). Without the seam S13 fails on this tree.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HCGpJXhSZasJLU38ksDghe
A non-numeric MAM_READY_EMPTY_GIVEUP, SKS_EMPTY_GIVEUP, SKS_IDLE_RETRIES,
SKS_IDLE_RETRY_BACKOFF_S, MAM_LOCK_STEAL_RETRIES, MAM_DIFF_MAX_BYTES,
MAM_DIFF_MAX_LINES or RECONCILE_POLL_INTERVAL was a `[` error or a sleep
error at the point of use (PR #43 review claude R3). They now go through
mam_int_knob: decimal, a warning and the default for a bad value. Minimums
are in test_issue26_ints.py INT_KNOBS: 1 for the give-up counts (0 acts as
1), the diff caps (0 truncates every diff) and the poll interval (0 is a
busy loop); 0 for the retry counts (one attempt) and the retry backoff.
SKS_QUIESCENT_INTERVAL stays raw: its default is 0.5 s and sleep's
fraction is its meaning; NOT_ARITHMETIC says so.
loop_lock.sh and diff_collect.sh also run without lib.sh (the Python runner
and the tests source them alone), so mam_int / mam_int_knob move verbatim
to lib_int.sh, which lib.sh sources and those two source when the function
is missing. remove.sh's no-manifest fallback list names the new file
(install copies every file under .agents/skills). test_issue21_loop_b l15,
which builds a control root holding only diff_collect.sh, copies it too.
Tests: the table guard now reads every shell file; scripts sourced alone
read their knobs as decimal; _pane_quiescent with SKS_EMPTY_GIVEUP=abc
gives up with a warning and no `[` error (14 of the new cases fail at
0051fd6).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HCGpJXhSZasJLU38ksDghe
MAM_WAIT_GRACE_S silently fell back to 300 on anything but bare digits
(" 30 " too), MAM_CHILD_WAIT_S went through float() (abc raised ValueError,
0.5 and 1e3 were taken) and MAM_JOB_TREE_MAX through int() (abc and an
empty value raised). All three now go through runner._int_knob, which is
_positive_int's rule (PR #43 review grok): decimal, blanks around allowed,
an invalid value warns once and the default is used. Minimums:
MAM_WAIT_GRACE_S >= 0 (wait exactly the budget), MAM_CHILD_WAIT_S >= 0
(look once; test_issue34 uses 0), MAM_JOB_TREE_MAX >= 1 (a cap of 0 calls
every tree "over"; not waiting is MAM_CHILD_WAIT_S=0).
The loop SKILL.md now names MAM_WAIT_GRACE_S in the budget row and the
sub-job paragraph (PR #41 M6), with the knobs' integer rules.
Tests: RUNNER_INT_KNOBS in test_issue26_ints.py holds the minimums; the
real wait_for_descendants is driven per knob, and a static check ties the
call-site minimums to the table (15 of the new cases fail at 0051fd6; the
14 that pass are valid values whose result did not change).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HCGpJXhSZasJLU38ksDghe
PR #43 review (grok):
(a) A UTF-8 byte-order mark at the start of the file made the first line an
"invalid key", so its setting was dropped. The one parser (envfile.py,
used by the wrapper and mqtt_common) now reads with utf-8-sig.
(b) A key given twice keeps its first value (a later line does not replace
it). The behaviour is unchanged; .mam.env.example's FORMAT section and
envfile.py's docstring now say so.
(c) MESSAGING.md said a MAM_ENV_FILE naming no file logs an error and makes
connections fail closed. Both loaders skip it silently and refuse the
ambient search; a file that exists but cannot be read is the error
(EnvFileError, one ERROR line and rc 1). The text now says that.
Tests A7: BOM in both loaders, first-value-wins in both loaders plus the
FORMAT text, and a missing explicit file loading neither it nor the ambient
.mam.env without an error plus the MESSAGING text (all three fail at 0051fd6).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HCGpJXhSZasJLU38ksDghe
A .mam.env that exists but cannot be read or decoded stopped the Python
entry points with an EnvFileError traceback, while the wrapper printed one
`ERROR:` line and exited 1 (PR #43 review claude S1). The mains that load the
env file - publish_event, registry, job_subscriber, cli, bench, heartbeat and
remote - now call mqtt_common.load_env_or_report(), which prints
`ERROR: <path>: cannot read (<exception type>)` and lets the main return 1.
No value or file content is printed. ensure_env_loaded() still raises: no
library function exits the process.
Test: every entry point, for a 000 file and an undecodable one, ends with
exactly that line and rc 1 and creates nothing (14 cases; all 14 fail at
0051fd6 with a traceback).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HCGpJXhSZasJLU38ksDghe
Issue #26: one .mam.env parser for the wrapper and the Python tools,
decimal integer knobs, tests on a local MQTT broker. Merge-workspace
review: round 1 (@b58edac) claude agy PASS, codex NOT PASS (R1-R4), grok
no verdict (its late report, archived as report-c9ed5b14.md, found R1 too);
round 2 (@0eec795) 4/4 PASS. Reports and round-2 identity sidecars go to
.agents/reports/<session>/.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VCgu9Fa9iT7TbJUSzdq4Ff
Merge-workspace review of PR #43 (codex R1-R4, claude R1/R2).
- R1: envfile.parse raises EnvFileError when the file exists but cannot be
read or decoded as a whole; `--shell` prints the cause and exits 1, so the
wrapper stops (rc 1, as before #26) instead of running on defaults, and
mqtt_common's entry points stop on the same error. A bad single line is
still a warning. The wrapper's message no longer claims a read failure
when the cause is elsewhere ("cannot load ... see the line above").
- R2: lib.sh mam_int spells out the ASCII blanks and digits instead of
[[:space:]]/[0-9], which follow the locale: U+2003 30 U+2003 was 30 in the
wrapper and invalid in the runner under en_US.UTF-8. The test oracle
_expected uses the same ASCII rule.
- R3: an integer flag given explicitly with an empty value is refused like
any other invalid value; only an absent flag keeps its default.
- R4: a line holding a NUL byte is skipped with a warning by both loaders;
before, the wrapper read "leftright" and the Python loader died.
- .mam.env.example states the format: no expansion, `export` and bash's own
variables skipped, a trailing `# ...` is part of the value, the environment
wins, an unreadable file is an error.
Tests: unreadable (0000) and invalid-UTF-8 files stop the wrapper and the
Python loader; a NUL line is skipped by both; Unicode blanks/digits are
invalid for mam_int, _positive_int, the wrapper and the runner under C and
en_US.UTF-8; explicit empty values for the five integer flags are refused.
All of them fail on b58edac.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VCgu9Fa9iT7TbJUSzdq4Ff
R1 (P1): a quoted export still ran code when the key was a bash special
variable (RANDOM=a[$(cmd)] is evaluated arithmetically on assignment).
envfile.RESERVED (bash's own variables, plus BASH_/COMP_/READLINE_
prefixes) is skipped with a line-numbered warning by both loaders; a test
keeps it covering every variable a clean bash defines. The wrapper also
hands SCRIPT_DIR/REPO_ROOT/TARGET_ENV to the parser as environment, so the
file cannot replace the variables it has already set.
R2 (P2): SKS_QUIESCENT_TRIES reached `for ((i < tries))` through a function
argument; it is normalised at the call site (minimum 0). B5 now requires
every integer-looking env default in the shell code to be normalised or
listed in NOT_ARITHMETIC with where it goes, and exercises _pane_quiescent.
R3 (P2): _positive_int strips leading zeros and rejects more than nine
significant digits before int(), like mam_int; 5000-digit inputs no longer
raise in the runner.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
bash read MAM_JOB_TIMEOUT_S=0700 as octal 448 (and failed on 0900) while
the loop runner read 700. One rule now, with a per-knob minimum:
lib.sh mam_int / mam_int_knob and runner._positive_int (blanks allowed,
digits only, decimal, min <= n <= 999999999).
- minimum 1: MAM_JOB_TIMEOUT_S, MAM_HEARTBEAT_SEC, MAM_HEARTBEAT_MISSES,
MAM_ACK_TIMEOUT_S (invalid env: warning + default) and the wrapper's
--timeout/--idle-timeout/--heartbeat/--heartbeat-misses/--ack-timeout
(invalid: rc 1); the runner's job_budget, --job-timeout, contract_args.
- minimum 0 (0 = check once): MAM_INJECT_ACK_GRACE_S,
delegate_wait_started's ack_s, SKS_DIALOG_TIMEOUT, SKS_BUSY_TIMEOUT,
SKS_DELIVERY_GRACE_S.
- tests/test_issue26_ints.py: INT_KNOBS is the one table of minimums; a
static guard keeps env defaults out of arithmetic and checks each
normalised knob against it.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- lib_py/delegation/envfile.py (stdlib only) holds the one set of rules:
comments and blank lines skipped, key and value stripped, one matching
quote pair removed, no shell interpretation, keys must match
^[A-Za-z_][A-Za-z0-9_]*$ (bad or `=`-less lines warn with the line
number, never the value).
- mqtt_common._parse_env_file delegates to envfile.apply.
- The delegate-job wrapper runs envfile.py --shell by path and evals the
shlex-quoted exports; values never reach a command line. The environment
now wins over the file in both loaders.
- .mam.env.example: commented assignments no longer use $HOME, which the
parser keeps literally.
The shell parsed the env file in one place only (wrapper :38), not three.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Issue #33 (job budget, wall_clock_timeout vs deadline_timeout) and
Issue #30 (notify-only stall watcher). Reviews of PR #41 in the merge
workspace: round 1 (@1673818) claude N1 / codex R1 R2 NOT PASS, agy grok
PASS; round 2 (@af0a2a2) grok N1 / codex D1 D2 NOT PASS, claude agy PASS;
round 3 (@9200562) 4/4 PASS. Reports and the round-3 identity sidecars go
to .agents/reports/<session>/. The design consensus on items A-D is in the
VERSIONS.md entry.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VCgu9Fa9iT7TbJUSzdq4Ff
grok N1: the wrapper spent up to 5 s on a TERM budget before it finalized the
job, so when the watcher swallowed the TERM the silent job's close came ~5 s
late and a `completed` written in that gap won (test_issue14 idle-grace).
codex D1: `_notify` blocks on a publish for up to 120 s, and the prompt went
out right after it; a completed, a re-dispatch or an unreadable record in that
window still got the nudge. codex D2: the wrapper pid was checked only at the
loop head, so a watcher whose wrapper vanished during a wait could still
notify and nudge once.
- multi-agent-mux-delegate-job `stop_stall_watch`: KILL + wait, no budget.
The watcher holds nothing to flush (its TERM handler is a bare os._exit),
and KILL cannot be swallowed.
- lib_py/stall_watch.py: `_wrapper_gone()` after every wait (before any
notice) and at the loop head; `_may_prompt()` right before the keys - the
wrapper is alive and the record, read then, is open and this dispatch;
`_dispatch_open(strict=True)` treats an unreadable record as "no".
- SKILL.md: the lifetime contract states the one-wait lag and that nothing is
sent after the wrapper is seen gone.
- tests/test_issue30_stall_watch_stop.py: the stop returns at once against a
TERM-ignoring stand-in (took 6 s on the round-2 code); completed,
re-dispatch and a torn record during the notice publish withhold the nudge;
a wrapper gone during the wait gets no notice and no nudge. All five fail
on the round-2 code.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VCgu9Fa9iT7TbJUSzdq4Ff
Round-1 review of PR #41 (claude N1, codex R1/R2).
N1 - the wrapper stopped its stall watcher with `kill` followed by an
unbounded `wait`. A TERM that lands in the watcher's fork-exec window is
swallowed (bash defers terminating signals in the forked child until the
exec), the watcher then installs its own handler and lives until the job
closes, and the wrapper hung until someone killed the watcher by hand
(reproduced twice in test_issue14's ack test; the wrapper trace stops at
`kill` + `wait`).
R1 - a wrapper that is itself terminated left the watcher orphaned.
R2 - a `completed` or a re-dispatch that landed during a blocking herdr
wait (up to 60 s) was still followed by the idle notice and the nudge.
- multi-agent-mux-delegate-job: `stop_stall_watch` sends TERM, polls up
to 5 s, then KILLs and reports "ignored TERM; killed"; `start_stall_watch`
passes `--watch-pid $$`.
- lib_py/stall_watch.py: `--watch-pid` (rc 0 once that pid is gone, checked
between herdr calls); `_dispatch_open()` re-reads the record after every
wait and right before the nudge - terminal status, another dispatch token
or attempt, or a missing record ends the run without a notice; a refused
`stalled:idle` publish withholds the nudge (`_notify` returns False).
- delegate-job SKILL.md: the watcher's lifetime contract; exit-code rows 2
and 3 name the idle clock and the wall-clock label; "before v4.7.5" ->
v4.8.0 (M5, NB2).
- tests/test_issue30_stall_watch.py (M8): the module-wide Linux mark is
narrowed to S6 (/proc); r4's stub stamps time.time() so its cross-process
comparison holds on macOS too (47 passed, 1 skipped here).
- tests/test_issue30_stall_watch_stop.py (new, macOS and Linux): the stop
routine against a TERM-ignoring stand-in returns in 4-12 s; the wrapper
returns (rc 3) with a TERM-ignoring watcher shim; `--watch-pid` ends the
watcher; a TERM to the real wrapper leaves no watcher; a job completed or
re-dispatched during the wait is not nudged; a refused notice withholds
the nudge. Every one of them hangs or fails on the round-1 code.
Not in this commit (follow-ups): M7 test hook in product code (no adapter
is unreliable, a seam is needed), M9/B3 public-broker latency (on this host
even `started` sometimes never reaches the subscriber), the leading-zero
budget parse (NB1) and M1/M2/M4/M6 go on the #17 item 4 list.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VCgu9Fa9iT7TbJUSzdq4Ff
- job_subscriber.py returns only named codes (RC_COMPLETED 0, RC_ERROR 1,
RC_NO_EVENT 2, RC_BROKER_UNAVAILABLE 3, RC_WALL_CLOCK 4). The wrapper
mirrors them as SUB_RC_* and compares subscriber codes only by name; a test
keeps the mirror equal to the Python constants and forbids numeric
comparisons of $sub_rc/$sub_exit and numeric `return` in the subscriber.
- `delegate-job wait` passed the subscriber's code straight through, so a
spent budget would have reached its callers as 4; it is 2 again (B7 fails
without the mapping).
- tier1 G-8 gave both clocks 0.5 s and raced; the wall clock now runs out
first by construction (idle 30 s) and the test asserts RC_WALL_CLOCK.
Other subscriber rc asserts use the names.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- input_region: in the prompt-line shape the input box starts only at a
column-0 prompt (codex indents a draft's continuation lines), and the
prompt and the (whole-line) placeholder are stripped from the box's first
non-blank line only, so `› Explain this terminal prompt:\n ›` is not empty.
- test_r4 runs with S=40 again: the defective code nudged ~30 s after a
missed transition, which S=10 could not tell from the fixed ~10 s.
Both new checks fail against the defective versions (stall_watch.py at
47e4274 -> 30.24 s < 40; input_region.py at bf0f5c1 -> nudge sent) and pass
now, each with its passing twin.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- R1 (P1): without rules the input region runs from the last prompt line to
the end of the pane; only a last line matching the adapter's footer pattern
(codex: ` <model> · ~/<cwd> · …`) is dropped, so a draft on a second line
keeps the nudge withheld.
- R2: while the synchronous submit runs, a relay thread finds the job it
registers (same session, created since the submit) and prints its
stalled:/stall_watch: notices; before, they appeared only after the job.
- R3: the broker-unavailable disk wait that runs into the deadline is the wall
clock: wall_clock_timeout (caller rc stays 3).
- R4: a state_change_seq change seen right before the judgement restarts the
idle window (decision 9: S seconds of continuous idle).
Regression tests are the reviewer's reproductions, each with its passing
twin; the wrapper-level #30 tests now use this environment's broker instead
of the #18 harness's public default.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
lib_py/stall_watch.py runs beside the wrapper's subscriber for a local herdr
job (started after delivery, stopped when the subscriber ends; MAM_STALL_WATCH=0
turns it off). It follows `herdr agent wait` transitions and publishes only
`progress` events through one publisher; it has no path that closes a job.
- blocked: `stalled:blocked <detection line>` once per episode, never answered.
- idle for MAM_STALL_IDLE_S (600) with no background descendants of the agent
pid (pane process-info + /proc; adapter resident_children and the heartbeat
timer excluded) and an empty input box: `stalled:idle` and one nudge.
- input box judged from adapter facts measured on herdr 0.9.1 (codex '›',
grok frame '│', opencode '┃' block + stop pattern); the whole-pane fallback
is gone. No facts: withheld + `stall_watch:input_check_unavailable` once;
never empty for 3 x S: `stall_watch:input_never_empty` once.
- herdr failures are not "no event": warning + `stall_watch:herdr_unavailable:
<code>` (or agent_not_found), backoff, rc 2 after MAM_STALL_HERDR_FAIL_S
(120); the wrapper prints the watcher's last lines.
- remote and human jobs are skipped with one log line.
- agent_status_reliable is an adapter field; false turns idle judgement off.
- the loop runner relays stalled:/stall_watch: notices once each.
- scoped_env drops a pane-inherited workspace scope for name lookups (#34 rule).
The module sits at the top of lib_py: delegation and loop may not import the
agent adapters (their sibling-import rules). Idle pane captures of the five
CLIs are fixtures; the mock herdr answers process-info in the real shape.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- wrapper: TIMEOUT falls back to MAM_JOB_TIMEOUT_S (--timeout > env > 3600);
an invalid value warns and keeps 3600.
- loop: --job-timeout <sec> (run_loop.sh passes it on; refused in the legacy
shell loop). The runner always hands the wrapper --timeout, so the budget
the wrapper registers is the one its wait caps come from.
- runner: wait_for_job and the MAM_CHILD_WAIT_S default are budget + 300 s
(MAM_WAIT_GRACE_S), today's 3900 with no option; an explicit
MAM_CHILD_WAIT_S still wins.
- subscriber: the wall-clock budget returns 4 (RC_WALL_CLOCK), silence keeps
2 (RC_NO_EVENT). The wrapper maps both to caller rc 2 and labels the close
from the rc: wall_clock_timeout vs deadline_timeout; the disk-heartbeat
grace that ends on the deadline is the wall clock too.
- registry close accepts wall_clock_timeout (engine: -> error); the remote
runner's deadline and command-timeout details lead with wall_clock_timeout;
the sub-job table files it CLOSED-UNCONFIRMED (first token, colon stripped).
Test expectations changed only where the contract changed: the loop's
contract_args now starts with --timeout, the subscriber's exit-code docstring
names rc 2/4, and the registry --help capture lists the new close kind.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Issue #34: the loop waits for the creator job's sub-jobs, reviewers get
the sub-job table as evidence, a run with sub-jobs voids a round whose
source changed during review, and a pane caller reaches an agent of
another workspace on its own server. VERSIONS.md carries the entry; the
merge-side reports (round 1 @ed293dc and round 2 @e80186f with identity
sidecars, base ed293dc -> head e80186f, evidence review-tree) are archived
under .agents/reports/<session>/.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VCgu9Fa9iT7TbJUSzdq4Ff
remote.py closes a job whose end it could not see with
`error --detail "deadline_timeout (remote runner)"`; the sub-job table
matched the reason exactly and filed it as a plain failure, losing the
unconfirmed count and the late-write warning (merge review, codex R2).
The kind is the first word of the reason now. Test T14 replays the
remote runner's close through the real registry and producer; it fails
without the fix.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VCgu9Fa9iT7TbJUSzdq4Ff
- registry.get_feedback only returned the detail of the last completed or
error event, so a sub-job the wrapper cancelled before injection
(target_not_found, session_busy) reached the review table as a bare
`cancelled` and its reason was lost (merge review, grok N1). get_feedback
takes the event kinds to read (default unchanged); the table asks for
cancelled too and shows NOT-DISPATCHED with the reason. Test T13, both
reasons, fails without the fix.
- the [귀속되지 않은 열린 잡] line listed jobs registered without
--parent-job but gave the reviewer no rule for them - the one case the
table cannot show (claude K1). A rule sentence follows the line whenever
such a job exists; without one the prompt is unchanged. T6 pins it.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VCgu9Fa9iT7TbJUSzdq4Ff
- mam_herdr: for name lookups (agent / has-session / kill-session) a
HERDR_WORKSPACE_ID that is the caller pane's own workspace (it matches
the HERDR_PANE_ID prefix) is dropped. Live agent names are unique per
server (herdr --skill), so this cannot address a same-named agent of
another workspace; an id the caller chose, or one set outside a pane,
still scopes (H-18/H-21/H-23). The generated shim is unchanged (S11).
- wrapper: a preflight that cannot see the target closes the job
cancelled with detail target_not_found instead of session_busy; the
loop's sub-job table counts it as NOT-DISPATCHED.
- tests: T10-T12 with the measured pane env (same-server socket, caller
w6, target w2); T8 follows the sub-job-armed guard.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Without --worktree/--base the guard fingerprinted the source on every
loop, so a loop whose source holds untracked files that change on every
job voided each round: test_tier4_e2e scenario 5 keeps the mock herdr's
state file (rewritten on each herdr call) in its repository and failed
with rc 1 on 3fdbb62 (passed on 7a4a0c2). A loop without sub-delegation
now behaves as before (issue #34 requirement 3); with sub-jobs the guard
protects against a deadline-closed sub-job still writing.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
round_roots was replaced by the correction job, so an implementation
job's open or failed sub-job vanished from the next review and the loop
could pass (planner-reviewer-codex-01, P2). The run's creator jobs now
accumulate; each wait still covers only the new job's tree, so the wait
cap is not paid again per round. T9 covers open / error / completed.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
GodopuandClaude Opus 5.5