* test(#4395): prove the manager spawns its debugger without blocking
Failing-first regression coverage for #4395.
debug.md:209 mandates the orchestrator to session-manager spawn carry
run_in_background: false, and says why outright: "Claude Code backgrounds
subagents by default, and only that flag makes the spawn return the
compact session summary directly" (#2196).
The session-manager to debugger spawn, one level down, carries no flag.
Measured: run_in_background appears nowhere under agents/ -- only in
gsd-core/workflows/. So by the rule #2196 itself states, that spawn is
backgrounded, Step 3 ("Handle Agent Return") has no return to inspect,
the manager emits CONTINUE_REQUIRED, the orchestrator auto-resumes per
#2257/#3448, and a second detached debugger races the first on
.planning/debug/<slug>.md.
Row 4 is the load-bearing one: it closes the CLASS by requiring every
subagent spawn under agents/ to declare run_in_background explicitly, so
the next agent that spawns one has to decide rather than inherit a silent
host default. It is scoped to agents/ precisely so it cannot misfire on
the workflows that deliberately use true for parallel fan-out.
Rows 5-7 are pins, not fixes: the #2196 mandate one level up, Step 2 as
the single spawn-format source that the eight continuation sites delegate
to, and the survival of CONTINUE_REQUIRED (which has a legitimate trigger
unrelated to this defect).
Red round: 4 of 7 rows fail. Row 3 needed hardening first -- asserting
only that the two variants AGREE passed vacuously, because two missing
flags are also equal; it now asserts each is present before comparing.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix(#4395): make the manager's own debugger spawn blocking
The orchestrator-to-manager hop already requires a blocking spawn and says
why (#2196, debug.md:209): Claude Code backgrounds subagents by default,
and only run_in_background=false makes the spawn return its summary. The
manager-to-debugger hop, one level down, carried no flag -- measured,
run_in_background appeared nowhere under agents/ at all.
So that spawn was backgrounded. Step 3 ("Handle Agent Return") opens
"Inspect the return output for the structured return header" -- with
nothing to inspect, the manager correctly declined to fabricate a terminal
summary and returned CONTINUE_REQUIRED; the orchestrator correctly
auto-resumed (#2257/#3448); the resumed manager reached Step 2 and spawned
a SECOND detached debugger. Both then raced on .planning/debug/<slug>.md.
Every observable in the report follows with no further assumption,
including the count: the reporter saw exactly three collisions in one
invocation, and debug.md:251 caps auto-resumes at three per slug -- one
collision per cycle.
Fixed at the cause, in both shipped variants, kept byte-consistent. The
eight continuation sites say "see Step 2 format", so they inherit it.
The issue offered two remedies. The second -- have the auto-resume path
reconcile a still-running debugger before spawning another -- is not taken:
it treats the symptom, and needs machinery that does not exist (no portable
way to enumerate or stop another runtime's live agents, plus an in-flight
sentinel with staleness and recovery rules, or an orphaned marker deadlocks
the session permanently). With the spawn blocking, the manager cannot reach
Step 4 while a debugger is live, so such a guard would also be unreachable.
#2257, #3448, the anti-loop heuristic, the cap of three, and the
CONTINUE_REQUIRED shape are all correct and untouched. CONTINUE_REQUIRED
keeps its legitimate trigger: the manager genuinely exhausting its own turn
budget mid-investigation.
Also corrects the red-round test to the canonical CALL form. debug.md
writes run_in_background=false inside Agent(...) and run_in_background:
false in prose; the first draft asserted the prose form, which the shipped
call would never have matched.
Emitted-Drift-Ack-Growth: gsd-debug-session-manager.md — the blocking spawn flag plus the note recording why an unstated flag produced colliding debuggers
Emitted-Drift-Ack-Growth: gsd-debug-session-manager.compact.md — same change as its full sibling, kept byte-consistent with it
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* chore(#4395): add changeset fragment
pr:0 placeholder is backfilled with the real number once the PR exists.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* chore(#4395): refresh the variant benchmark baseline
Two entries move.
gsd-debug-session-manager.md 4766/4477 -> 4938/4649 is this change: the
blocking-spawn flag plus its explanatory note, added to BOTH variants to
keep them byte-consistent, so the compact sibling grows by the same amount
and the pair's reduction ratio dips 6.06 -> 5.85. The compact file remains
strictly smaller than its canonical sibling, which is what the variant
guard's size check actually requires.
gsd-code-fixer.md 10741 -> 10740 is NOT from this branch -- the file is
untouched here. It has scored 10740 since f334f277dd (#4324) reworded a
line without refreshing this fixture, so the stale number is sitting on
next. Fixed here rather than deferred; the #4350 branch carries the
identical one-token correction, so whichever lands first makes the other a
no-op.
Refreshed with the variant script's own --write.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix(#4395): state the blocking rule agent-wide and correct two overclaims
Review round. Three substantive corrections, one of them to a claim I made
in the previous commit message.
1. The blocking rule is now stated AGENT-WIDE, not per-call. My earlier
claim that "the eight continuation sites say 'see Step 2 format', so
they inherit it" was false: exactly ONE of them names Step 2 (the
compact variant says "Step 2 format" without the "see", which is why
the first draft of the test matched it zero times there). The other
sites inherit only because Step 2 holds the sole Agent() spawn literal
in each file. Both variants now say so outright, and the test pins the
sole-literal invariant in BOTH variants rather than the prose wording
in one.
2. debug.md's two auto-resume buckets now restate run_in_background=false
for the re-spawn. "The same session_params" does not carry it --
session_params is prompt content, not the spawn flag.
3. The test extractor now also matches single-line Agent(...) calls. The
class guard was blind to exactly the shape a future offender is most
likely to take.
Also corrects the diagnosis: remedy 2 is NOT unreachable once the spawn
blocks. This agent's own retained CONTINUE_REQUIRED trigger is "turn
budget exhausted WHILE THE DEBUGGER IS STILL INVESTIGATING", so a harness
turn cutoff mid-wait still double-spawns; debug.md:209 names the same
class from the other side. What this fix removes is the SYSTEMATIC case --
every invocation, because the spawn was always backgrounded. The residual
turn-cutoff window survives, bounded by the existing three-resume cap, and
is stated in the PR rather than denied.
Emitted-Drift-Ack-Growth: gsd-debug-session-manager.md — blocking spawn flag, the note recording why an unstated flag produced colliding debuggers, and the agent-wide restatement the per-site inheritance actually depends on
Emitted-Drift-Ack-Growth: gsd-debug-session-manager.compact.md — same change as its full sibling, kept byte-consistent with it
Emitted-Drift-Ack-Growth: debug.md — both auto-resume buckets restate the spawn flag, since session_params does not carry it
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* chore(#4395): backfill the changeset PR number
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
---------
Co-authored-by: sim <sim@local>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
Tom Boucher
@@ -149,7 +149,7 @@ specialist_dispatch_enabled: true
|
||||
|
||||
Display the compact summary returned by the session manager.
|
||||
|
||||
**Return handling — exhaustive, no fallthrough (#2257).** Apply the same three-way classification as Section 4 "Session Management" below: `DEBUG SESSION COMPLETE` and `ABANDONED` are the only two terminal shapes. ANYTHING ELSE — including the explicit `## CONTINUE_REQUIRED` marker and any unrecognized or malformed summary that is not one of the two terminal markers — is non-terminal. Read `.planning/debug/{SLUG}.md` for the current `status`/`next_action` and AUTO-RESUME by re-spawning `gsd-debug-session-manager` with the SAME `SLUG`/`debug_file_path` and the same `session_params` as the spawn above PLUS the resume parameters (#3448): `resume: true`, `resume_status: {status}`, `resume_next_action: {next_action}`, both sourced from `.planning/debug/{SLUG}.md`. The respawn must NOT be parameter-identical to a cold start: identical params drop the recorded next action and the disposition that any earlier checkpoint in the session was already answered, so the debugger re-derives — or stalls before — the very step the checkpoint already names (the #3448 auto-resume stall). Do NOT return control to the user, and do NOT report the session as complete.
|
||||
**Return handling — exhaustive, no fallthrough (#2257).** Apply the same three-way classification as Section 4 "Session Management" below: `DEBUG SESSION COMPLETE` and `ABANDONED` are the only two terminal shapes. ANYTHING ELSE — including the explicit `## CONTINUE_REQUIRED` marker and any unrecognized or malformed summary that is not one of the two terminal markers — is non-terminal. Read `.planning/debug/{SLUG}.md` for the current `status`/`next_action` and AUTO-RESUME by re-spawning `gsd-debug-session-manager` with the SAME `SLUG`/`debug_file_path` and the same `session_params` as the spawn above PLUS the resume parameters (#3448): `resume: true`, `resume_status: {status}`, `resume_next_action: {next_action}`, both sourced from `.planning/debug/{SLUG}.md`. The respawn must NOT be parameter-identical to a cold start: identical params drop the recorded next action and the disposition that any earlier checkpoint in the session was already answered, so the debugger re-derives — or stalls before — the very step the checkpoint already names (the #3448 auto-resume stall). The re-spawn carries `run_in_background=false` exactly as the original spawn does (#2196): `session_params` is prompt content, not the spawn flag, so "the same `session_params`" does not carry it. Do NOT return control to the user, and do NOT report the session as complete.
|
||||
|
||||
**Anti-loop guard.** Same two-stop policy as Section 4 "Session Management": (1) a no-progress heuristic keyed on `next_action` ALONE from `.planning/debug/{SLUG}.md` — never `updated`, which is overwritten on every checkpoint write (`agents/gsd-debugger.md`: "Update the file BEFORE taking action"), so it changes every cycle and can never signal no-progress. Two consecutive auto-resumes with `next_action` UNCHANGED stop the loop and print a blocker report to the user (checkpoint path, status, next_action, "N auto-resumes made no progress"). And (2) an absolute hard cap, independent of content: the orchestrator tracks a running total of auto-resume spawns for this `SLUG` within the current `/gsd:debug` invocation; after **3** total auto-resumes for the slug, STOP auto-resuming and emit the blocker report REGARDLESS of whether `next_action` changed. The hard cap is the guaranteed termination bound; the no-progress heuristic is only a faster early exit before the cap is reached.
|
||||
|
||||
@@ -243,7 +243,7 @@ Display the compact summary returned by the session manager.
|
||||
|
||||
1. **Terminal — complete.** Summary shows `DEBUG SESSION COMPLETE` (without an `ABANDONED` status line): the session is finished. Stop.
|
||||
2. **Terminal — abandoned.** Summary shows `ABANDONED`: note session saved at `.planning/debug/{slug}.md` for later `/gsd:debug continue {slug}`. Stop.
|
||||
3. **Non-terminal — auto-resume.** ANYTHING ELSE — including the explicit `## CONTINUE_REQUIRED` marker and any unrecognized or malformed summary that is not one of the two terminal markers above — is non-terminal. Read `.planning/debug/{slug}.md` for the current `status` and `next_action`, then AUTO-RESUME by re-spawning `gsd-debug-session-manager` with the SAME `slug`/`debug_file_path` and the same `session_params` as the spawn above PLUS the resume parameters (#3448): `resume: true`, `resume_status: {status}`, `resume_next_action: {next_action}`, both read from `.planning/debug/{slug}.md`. The respawn must NOT be parameter-identical to a cold start: identical params drop the recorded next action and the disposition that any earlier checkpoint in the session was already answered, so the debugger re-derives — or stalls before — the very step the checkpoint already names (the #3448 auto-resume stall). Do NOT return control to the user; do NOT report the session as complete.
|
||||
3. **Non-terminal — auto-resume.** ANYTHING ELSE — including the explicit `## CONTINUE_REQUIRED` marker and any unrecognized or malformed summary that is not one of the two terminal markers above — is non-terminal. Read `.planning/debug/{slug}.md` for the current `status` and `next_action`, then AUTO-RESUME by re-spawning `gsd-debug-session-manager` with the SAME `slug`/`debug_file_path` and the same `session_params` as the spawn above PLUS the resume parameters (#3448): `resume: true`, `resume_status: {status}`, `resume_next_action: {next_action}`, both read from `.planning/debug/{slug}.md`. The respawn must NOT be parameter-identical to a cold start: identical params drop the recorded next action and the disposition that any earlier checkpoint in the session was already answered, so the debugger re-derives — or stalls before — the very step the checkpoint already names (the #3448 auto-resume stall). The re-spawn carries `run_in_background=false` exactly as the original spawn does (#2196): `session_params` is prompt content, not the spawn flag, so "the same `session_params`" does not carry it. Do NOT return control to the user; do NOT report the session as complete.
|
||||
|
||||
**Anti-loop guard.** Two independent stops apply; the orchestrator honors whichever trips first:
|
||||
|
||||
|
||||
Reference in New Issue
Block a user