Repository navigation
fix(acp): compact opencode, and stop telling four backends they self-manage - #11942
Conversation
GPT 5.6 Review — ✅ no blocking findingsGPT 5.6 completed its review of This comment is updated in place on each push. Review detailsFINDING -- src/kiro_crew/providers/acp.py:2020 -- False positive or not applicable? A repository writer can comment: |
Design Review (Fable 5) — 🟡 CONCERNSDesign-level review of Design-Verdict: CONCERNS Deepseek's session-destroying recycle ships before its warning: users lose conversation state at threshold with no advance nudge (#11949 deferred). WatchThe recycle arm for [DESIGN-REVIEWED] 6f154dc |
First Principles Review (Fable 5) — 🟡 CONCERNSPremise-level review of First-Principles-Verdict: CONCERNS The deepseek recycle arm auto-destroys sessions on a premise the author explicitly declines to claim — "I did not drive" the harness's own wall behavior. Not justified as shipped
What this change shipsInventory (10 items) — 8 justifiedIntent: stop lying to users on five backends about who compacts their context, and compact where it actually works — a FIX.
[FIRST-PRINCIPLES-REVIEWED] 6f154dc |
Opus 4.8 Review — ✅ no blocking findingsReviewed Review detailsThe discovery pass found no candidates. I independently traced the load-bearing paths — the three-arm gate ( No findings. [OPUS-REVIEWED] 6f154dc Verdict parsed from the review's SHA-scoped output markers for commit False positive or not applicable? A repository writer can comment: |
8ec1faa to
dbb4807
Compare
|
fixed — span=cfcec2aa057b (Blocker: inline completion patched at one call site)
|
|
fixed — span=3b442073bbbf (Item 9: symptom-level, cause is at the provider seam)
|
|
fixed — span=8f5b9a74ba8f (Item 5: three byte-identical copies of one wording)
|
dbb4807 to
b70963c
Compare
|
fixed — span=6cd5f1ca91ce (the specs still describe kiro/claude as the only members)
|
|
accepted-and-deferred — span=96f602a99be8 (the abrupt-restart UX gap has no owner)
|
|
rebutted — span=d93262893941 (fold out the caller-side
|
|
rebutted — span=8736e1077a95 (pi and goose rest on source, not a wire capture)
|
|
accepted-and-deferred — span=9525751fa34c (hoist the duplicated inline-completion pair)
|
99d1742 to
8b20ced
Compare
8b20ced to
5ca16f9
Compare
|
fixed — span=399217568b6f (recycle emits a false compaction-success notice)
|
|
fixed — span=1ebd9b37e14c (
|
|
rebutted — span=791bc5a19548 (Item 3: opencode proves an absent advertisement is not an absent capability)
|
|
fixed — span=e9511ffdba58 (Item 3: the remedy needs a recorded decision)
|
|
fixed — span=ceeae6a74edd (a failed kiro-cli compaction gets the uncompactable notice)
|
|
fixed — span=d098b2f2b140 (providers.md still describes a single decline)
|
|
fixed — span=6b560f2c2208 (a human should accept the interim warning gap)
|
|
fixed — span=1bd65a1f7be3 (Item 3: a spec-pinned decline replaced by the erasing arm)
|
|
fixed — span=399217568b6f (the outcome is dropped on the channel leg)
|
|
span=4ed124996b6e — the destructive arm and its pre-warning land in reverse order. Accepted; the sequencing is deliberate and #11949 carries the nudge. Your read of the state is right, and the description concedes it because it is true: the soft-threshold nudge is suppressed for every non-member, so a deepseek user's first signal is the after-the-fact restart notice. Why this order rather than the other. Without the recycle a deepseek session runs into its 8192-token wall and ends anyway — the same loss of history, no notice at all, and no bound on the context in between, which is half the bar this change exists to meet. Deferring deepseek's membership to ship alongside #11949 buys better sequencing of the same destruction at the price of leaving that leak open for a release. The ruling on this PR took that trade explicitly and is posted in this thread. What I did tighten is the part inside this diff's reach: the notice now names its CAUSE rather than only its outcome — Crew restarted the session because the harness has no compaction path — on all four surfaces, pinned by The pre-threshold nudge itself is #11949 ( |
|
span=0079fae88041 — the recycle's benefit rests on unverified wall behavior, so if deepseek does self-summarize Crew destroys live sessions at 70% for nothing. Accepted as the residual risk it is; the driven capture is out of my reach on this host and the surface stays removable. This is the correct question to ask of the previous round's correction. Taking the overreach out of the comment did not make the wall behaviour known — it made the not-knowing explicit, and you are right that the recycle's value is contingent on which way it resolves. Why I cannot close it here. The clearance is a driven capture of deepseek crossing its own window, and the deepseek captures in the corpus were taken off What bounds the residual in the meantime. The failure mode if the harness does summarize at the wall is a session restarted earlier than necessary — history lost that would have been summarized — which is bad and is bounded by being the same destination a FAILED compaction already reaches on every other backend, announced with its cause rather than as a compaction. The failure mode if it does not is a session that hits 8192 and ends with no bound and no notice. The membership is one frozenset entry ( I am recording this as accepted risk rather than answered, and it is a maintainer's call which way to resolve it — which is also what the first-principles lane is asking for on its own item. |
|
Note on the GPT lane's blocking finding from the previous head (
I did not take the pre-drafted override even though the adjudicator's harm rung (LOW, self-correcting) reads fair, because the thing it self-corrects to is the one sentence this change set exists to stop emitting: telling a kiro-cli user whose compaction merely failed that their backend cannot compact at all. Pinned by |
|
span=8cfe5de45371 — Item 2, the recycle-at-threshold default rests on a premise the diff declines to claim. Accepted; the premise cannot be settled from this host, so it goes to a maintainer decision rather than to another round of my own prose. The inheritance is real and I put it there: last round's correction replaced an unverified assertion ("its harness carries compaction internally") with an explicit non-claim, and the non-claim is honest about the same gap the assertion papered over. Making the premise visible does not discharge it. Of the two clearance paths, the driven capture is out of reach here rather than merely unspent. The corpus captures were taken off That leaves the maintainer record as the live path. The decision itself has already been made and is posted in this thread: the recycle stays, because the bar for this change is that context must not grow unbounded AND the text must be truthful, and letting a deepseek session run into its 8192-token wall fails the first half. What is missing is that decision recorded in the form this lane reads, which is a maintainer's to enter and not mine to self-authorize — a wrong override here ships exactly the class of unproven claim the fence exists to stop. For the record of what that decision is choosing between, since this is the part I can establish: the observable half is settled by the two committed captures — no |
buluoray
left a comment
There was a problem hiding this comment.
Reviewed at head a176e77d8ed0ce0db452a9145385f26d05269591. No blocking findings — approving on correctness. One item below is a product decision rather than a defect, and I want it named rather than buried: read point 1 before you merge.
Verified against source rather than the description — the hard invariant first, since this PR touches several backends' identity predicates:
- Positive identity holds everywhere. No touched predicate uses
not is_X.compaction_self_managedisbackend in ACP_BACKENDS_COMPACT or in ACP_BACKENDS_HARNESS_MANAGED;compaction_unmanaged_backendreturns an id onlyif backend in ACP_BACKENDS_CONTEXT_RECYCLE;compact_refusal_armchecks HARNESS_MANAGED, then CONTEXT_RECYCLE, then falls through to UNCLASSIFIED. Crucially the destructive recycle arm is granted only by explicit CONTEXT_RECYCLE membership, never by exclusion — checked acrosssession_compaction.py,providers/acp.py,providers/base.pyandmessaging/commands.py. - State loss on the changed path. opencode's move into
ACP_BACKENDS_COMPACT/INLINE_COMPACTIONcompacts in place, so process and session survive. The inlinecompletedshort-circuit fires only whenturn_finished_cleanly()(positiveend_turn, not cancelled), andtest_a_cancelled_turn_is_not_a_completed_compactionpins that — so a falsecompletedcannot silently reset the meter. - No hardcoded model id. The only fallbacks are
getattr(..., "backend", ACP_BACKEND_KIRO)— a backend id, matching the pre-existingmanual_compact_unsupported_backendpattern and failing safe to compactable / no-recycle — plusgetattrdefaults that fail CLOSED on test doubles (_compacts_inline,_inline_turn_finished_cleanly). - Files read:
session_compaction.py,providers/acp.py,providers/base.py,acp/session_handle.py,acp/session_provider.py,acp/client.py,messaging/commands.py,dashboard/state.py,chat_compaction_notice.py, the opencodecompact-live.jsonlfixture, and the 976-linetest_compaction_other_backends.py(seam, gate end-to-end, callback-outcome and refusal-text arms all pinned with stated RED-before states).
Needs your judgment, not a code change:
ACP_BACKENDS_CONTEXT_RECYCLE = {ACP_BACKEND_DEEPSEEK}— deepseek's recycle atautocompact_pctis destructive (it discards conversation memory) and it ships before the advance-warning nudge, since #11949 is deferred. A deepseek user therefore gets only an after-the-fact notice. Both advisory lanes raise exactly this. I am not treating it as blocking: it is positively gated by explicit membership, reversible with a one-line data change, and it replaces unbounded growth-until-window-death with a bounded restart. But it is a real tradeoff, and it compounds with point 2 — so if you would rather land the nudge first, say so and I will withdraw the approval.- That membership also rests on deepseek's unverified wall behaviour: the description concedes it was not driven to see whether deepseek self-summarizes at its own window. If it does, the 70% recycle discards memory a no-op would have preserved. Bounded and reversible, so not blocking, but it is the measurement that would retire point 1.
chat_runner.pykeeping the caller-sidecompacts_inlinegate is correct and your rebuttal to Design stands: the two arms differ by arole=compactingcomposer-disable broadcast, so folding them would change UI behaviour rather than delete dead code.
Bot verdicts on this SHA: GPT 5.6 no blocking findings; Opus 4.8 no blocking findings, having independently traced gate → _recycle_unmanaged → _recycle_held and falsified a recycle-loop hypothesis (the no-cooldown shape already exists on the pre-existing _compact_in_place failure path and has not looped, because real windows leave headroom); Design 🟡 CONCERNS and First Principles 🟡 CONCERNS, both advisory and both on the deepseek question above. The disposition comments citing dbb480 / b70963 are from prior revisions.
bolichen97
left a comment
There was a problem hiding this comment.
Approved: readiness gate passed
…manage
Crew only ran /compact for kiro-cli and claude. Every other backend got one
answer: skip it, and tell the user "this backend manages compaction
automatically". Driving each harness says that answer was right once out of five
times.
opencode DOES serve /compact and finishes it inside the prompt turn, on a live
capture, so it joins ACP_BACKENDS_COMPACT and ACP_BACKENDS_INLINE_COMPACTION. For
an inline member wait_for_compaction() answers from the capability instead of the
queue -- but only when the turn reached its own end boundary uncancelled, since a
cancelled turn compacted nothing. That answer sits on the WAIT because both routes
to a compaction reach it: the manual entry points via compact(), the autocompact
via stream_command("/compact").
KAS is the one correct skip, so the reason becomes a membership it can be checked
against: ACP_BACKENDS_HARNESS_MANAGED_COMPACTION.
deepseek compacts nowhere Crew can see, so a skip bounded nothing.
ACP_BACKENDS_CONTEXT_RECYCLE names it and its threshold now recycles through the
path a failed compaction already takes. The recycle is granted by membership and
never by exclusion: a harness in none of the three sets declines, and the gate
logs a WARNING naming the missing decision.
pi and goose look inline in source but could not be driven here, so they stay out
rather than join on the weaker evidence class (#11973). codex is the sibling
branch's item. All three now get a refusal that promises nothing instead of a
claim nobody had evidence for, chosen by one compact_refusal_arm() that every
surface maps to its own wording.
buluoray
left a comment
There was a problem hiding this comment.
Re-approving at head 6f154dc861e6fb18b0b217c9a9a28dcbca5a4606. My earlier approval was on a176e77d and was voided by the rebase under require_last_push_approval, which is correct behaviour, not a problem.
Checks are green at this head. 0 failing, 0 pending, PR Readiness SUCCESS, both CodeBuild aggregates SUCCESS. Six rows read as CANCELLED in the rollup — Automated Rule Check, GPT 5.6 Review, Screenshot Evidence, Inclusive Language, SAST (Semgrep), PR Hygiene — and each has a newer same-named SUCCESS started 8–76 seconds later, so they are concurrency supersessions of the pre-rebase dispatch, not failures. Collapsed to the newest attempt per check identity, everything is green.
Blocking lanes on this head: GPT 5.6 no blocking, Opus 4.8 no blocking. Design and First Principles are CONCERNS, which is advisory.
The rebase did not move anything I had verified. Re-read at 6f154dc8 rather than assumed:
ACP_BACKENDS_CONTEXT_RECYCLE = frozenset({ACP_BACKEND_DEEPSEEK})(agent_sdk/backends.py:983) — still one explicit positive member.- Every consumer answers from positive membership:
acp/session_provider.py:731,providers/acp.py:681,messaging/commands.py:375, eachbackend in ACP_BACKENDS_CONTEXT_RECYCLEwith anot isinstance(backend, str)guard ahead of it. Nonot is_X_backendanywhere in the diff, so harness identity stays positive per H5/H6. - No hardcoded model id in any added line.
The product tradeoff is unchanged and still the maintainer's to weigh, which is why I am approving the code rather than the rollout: a member of this set gets context recycle, which discards conversation memory, and the advance-warning nudge (#11949) is deferred — so a deepseek user learns about it after the fact rather than before. I judged that acceptable because the grant is explicit single-member, one line of data reverts it, and the alternative is growing until the window bursts. Two advisory lanes read it the same way. If you would rather land #11949 first, this approval should not be taken as arguing against that.
Not merging; that is the maintainer's call.
bolichen97
left a comment
There was a problem hiding this comment.
Approved: fix-class, readiness:passed, no conflict.
Problem / Motivation
Kiro Crew only ran
/compactfor two backends: kiro-cli and Claude. Every otherone got the same answer, and the same sentence:
That sentence is a claim about five harnesses. I drove each one. It is true about
one of them.
The skip is not only about the typed command.
_compaction_gate_decisionreadsthe same capability for the AUTOMATIC compaction, so a session on any of those
backends crossed
session.autocompact_pctand Crew did nothing at all — nocompaction, no reset, no retry, and no line telling anyone.
Why it matters
Two ways this hurts a user.
A user on opencode, pi or goose typed
/compact, got told their backend does itfor them, and it does not do it unasked. So their context filled up and nobody
compacted it. All three of those harnesses had a working
/compactthe wholetime.
A user on deepseek has it worse, because nothing Crew can see bounds their
context. deepseek's own window in my capture was 8192 tokens and the session sat
at 7695 of it, with no compaction command advertised, no compaction status on the
wire, and
session/loadanswering "Method not found". Whether its harnesssummarizes for itself at the wall I did not drive, and I claim it in neither
direction; what the capture settles is that no compaction path on that surface
answers a threshold Crew has already crossed. Crew read that number, decided the
harness had it covered, and let it grow.
What changed (motivation → approach → change)
I drove every backend outside
ACP_BACKENDS_COMPACTand asked four questions ofeach: does
/compactdo anything, does it finish inside the prompt turn, does theharness compact on its own and say so, and what does Crew do at the threshold.
/compactworks?opencode joins both compaction sets. It serves
/compactand finishes itinside the prompt turn, so the turn ending is the done signal. It is also the only
harness here with a driven capture, which is the bar: source says what the code
would do, a capture says what the harness did. pi and goose look identical in
source and have none, so they wait in #11973.
kas keeps its skip, and now has a set that says why. New
ACP_BACKENDS_HARNESS_MANAGED_COMPACTION. Its one member summarizes unasked andresets Crew's meter, so skipping costs nothing. Before, that was an absence, and an
absence records no decision.
The done signal for an inline harness lives on the wait. Membership alone
would have made things worse: the caller sends the prompt, sees no status, falls
into
wait_for_compaction— which an inline harness never answers — burns 300sholding the turn semaphore, then recycles a session that had just compacted. So
wait_for_compaction()answerscompletedfrom the capability, onAcpProviderand
AcpSessionHandle.That method is the choice, not a convenience: it is the one place BOTH routes
arrive. Seventeen call sites pair
provider.compact()with it; the autocompactpairs
stream_command("/compact")with it. A captured status still wins, and aCANCELLED turn withholds the answer — it compacted nothing, and a false
completedresets the meter and arms the cooldown.deepseek gets recycled instead of skipped. Third set,
ACP_BACKENDS_CONTEXT_RECYCLE. Its threshold reaches_recycle_unmanaged, where afailed compaction already lands — on the reason rather than after the timeout that
proves it. The arm falls THROUGH the gate rung, so
unconfirmed,in_progressandcooldownstill run first.The destructive arm is granted by membership, never by exclusion. A harness in
none of the three sets declines: ending a conversation is not something a harness
earns by never having been classified. The gate logs a WARNING naming the missing
membership, told apart from the settled case by a new
compaction_self_managed.And every arm says what it does. Three sentences — self-managed, recycled, and
one that promises NOTHING. codex, pi and goose are that third case; all three used
to be told their backend self-manages, on no evidence. The wording stays per surface
and the CHOICE does not: one
compact_refusal_arm()decides and five surfaces mapit. Two — the dashboard and iMessage — held one sentence covering all three cases.
Where each part lives
src/kiro_crew/agent_sdk/backends.pysrc/kiro_crew/agent_sdk/backend_cards.pysrc/kiro_crew/acp_backends.py,src/kiro_crew/acp/types.pysrc/kiro_crew/providers/base.pycompaction_unmanaged_backendon the ABC, defaultNonesrc/kiro_crew/providers/acp.py,src/kiro_crew/acp/session_provider.pysrc/kiro_crew/session_compaction.py_recycle_unmanaged, the WARNING for an unclassified backendsrc/kiro_crew/providers/acp.py,src/kiro_crew/acp/session_handle.pywait_for_compaction()answers inline members from the capabilitysrc/kiro_crew/session.pysrc/kiro_crew/messaging/commands.pysrc/kiro_crew/whatsapp/commands.py,src/kiro_crew/whatsapp/transport_dispatch.pysrc/kiro_crew/imessage/transport_dispatch.py,src/kiro_crew/dashboard/chat_runner.pysrc/kiro_crew/feishu/transport_dispatch.py,src/kiro_crew/wecom/transport_dispatch.py,src/kiro_crew/weixin/transport_dispatch.pydocs/system-specs/modules/session.md,docs/system-specs/modules/harness-onboarding.mdEvidence, per harness
/compactout of its PROMPT handler. Over four turnsusage_update.usedclimbed 14863 → 15727 → 16614 → 17478./compactreturnedstopReason: end_turnwith no status frame. The next ordinary turn read 14577, under the pre-compact peak, and the model answered from a summary of the dropped turns.prompt()intercepts/compactbefore any model turn, awaitssession.proc.compact(), raises if pi reports failure, emits oneagent_message_chunksaying "Compaction completed.", returns{ stopReason: "end_turn" }. Nothing follows. Its advertisedcompact+autocompactcommands are live in this repo's own corpus.compactis a published built-in. ACPon_prompt→Agent::reply→execute_commanddispatches it before a model turn, replaces the stored conversation, answers "Compaction complete". goose's owncommand_starts_turn("/compact")is false and its suite pins that.summarization_started/summarization_completedintest/fixtures/acp_frames/kas/steering.jsonl, mapped byacp.kas_wire, callingreset_after_compaction().available_commands_updateat all;session/loadis alreadyMethod not found; no compaction status in itssession/updatevocabulary. It does report a real meter:used7554 → 7695 ofsize8192 in one captured turn.pi and goose could not be driven live on this host — pi answers
Authentication requiredand gooseFailed to resolve provider: GOOSE_PROVIDER. Their source isquoted above because it is worth keeping, but source is not the bar this set holds
its members to, so they are deferred to #11973 rather than admitted on it.
Backwards compatibility
Compatible. kiro-cli and Claude take exactly the paths they took. kas keeps its
decline, its log line and its reply text word for word. The new ABC property
defaults to
None, so a provider that never declares it reads as self-managing,which changes nothing.
One behaviour change a user can see: a deepseek session at the autocompact
threshold is now restarted instead of left alone. It loses what the agent
remembered. The alternative was letting the context run into the harness's own
window, which loses the same thing and breaks every turn after it. The reply text
says which one happens.
The fail direction for a harness added later is deliberate and recorded on
ACP_BACKENDS_CONTEXT_RECYCLE: a backend joining none of the three sets declinesand is logged at WARNING, and is told the third sentence, which claims nothing. It
is not recycled. Granting the one session-ending arm by exclusion would be the
same defect as the false sentence this PR removes, only louder.
Tests
test/test_compaction_other_backends.py— 26 tests. Run against the unfixed base,20 fail, each naming the missing set, the missing property or the wrong
behaviour. The 6 that pass in both states are the regression guards: kiro-cli
keeps its async wait, kas stays untouched,
below_thresholdstill wins, and theinline set stays a strict subset.
The gate tests drive a real
SessionManagerand assert the things a decline and arecycle differ on: whether the prompt was sent, whether the status was awaited,
whether the entry was popped, whether the provider was shut down.
Updated:
test_manual_compact_gate,test_auto_compact_gate,test_acp_capability_sets_leaf,test_acp_goose_backend— each membership pinmoved deliberately rather than loosened.
test/test_codex_compaction.py— three tests from #11944, changed by the rebaserather than by this PR's own design. Its exact-membership pin names opencode too;
its two in-place-arm tests read the seam
wait_for_compactioninstead of_compact_in_place, which is where the arm this PR keeps lives. Everything #11944pinned about codex — the frame translation, the marked pair, the dangling-started
settle, both transports — is untouched and green.
Local, post-rebase: 580 tests green across the affected suites
(
test_codex_compaction,test_compaction_other_backends,test_manual_compact_gate,test_auto_compact_gate,test_acp_capability_sets_leaf,test_agent_sdk_capabilities,test_acp_goose_backend,test_session,test_channel_compaction_notice,test_harness_parity, the five messaging-surface dispatch suites andtest/metrics/test_business_counters). black, isort, flake8, comment-history,harness-parity, agent-sdk-boundary, feature-map and docs-lint all clean. The
whole-tree suite is left to CI on purpose — the host is under memory pressure.
Manual verification
The opencode numbers above are a real session, driven over stdio against the
installed binary. The probe drivers are not in this diff; they are throwaway
scripts, and what they produced is quoted above and in the code comments.
Screenshots / video
Not applicable — no UI change. The only user-visible strings are chat replies,
quoted in full above.
Related Issues
no linked issue: found by auditing the compaction memberships directly rather than
from a filed report, so there is no ticket to close.
Stacks on #11944 (
fix/codex-compaction), which has merged. It added codex tothese same two sets, so this branch is rebased on it and both memberships stand:
ACP_BACKENDS_COMPACTis{kiro, claude, codex, opencode}andACP_BACKENDS_INLINE_COMPACTIONis{claude, codex, opencode}. codex's membershipstays #11944's decision and its evidence; this PR carries opencode's.
One of its lines is replaced rather than kept. #11944 also answered the inline case
inside
_compact_in_place, by skipping the status wait for a member ofACP_BACKENDS_INLINE_COMPACTION. This PR answers the same case onwait_for_compactioninstead, and that is the one kept, because the manual entrypoints reach a compaction through
provider.compact()and never through_compact_in_place— an arm at that one call site leaves the other seventeen sitesstranding. The guarantee #11944 wanted there is unchanged: the wait returns at once
for an inline member instead of spending
COMPACT_WAIT_TIMEOUT_SECSwhile holdingthe turn semaphore. What changes is the outcome when an inline harness ends its
/compactturn having compacted nothing: #11944 recycled the session immediately,and now the coordinator's own post-compaction meter reading catches it one rung
later (cooldown, then a reset when the context is still critical). Two of #11944's
tests pinned the old location and are retargeted to the seam; one pinned the exact
membership of the two sets and now names four harnesses.
Tracked follow-ups: #11973 — capture pi and goose driving
/compact, then addthem to both sets. They look inline in source and this PR does not claim them,
because the set holds its members to a driven capture and neither could be driven
here. #11949 — The soft-threshold nudge is suppressed for every
non-member across the channel surfaces. That is right for kas — its
/compactadvice genuinely cannot work — but it means a deepseek user gets no warning before
the restart. Warning them needs a third nudge string per surface, because the
existing nudge tells them to run
/compact.Pattern harvest
Rule candidate: review-prompt
Pattern: a capability withheld by absence rather than by a recorded decision
An absence is not a decision. Four harnesses sat outside
ACP_BACKENDS_COMPACTfor four different reasons — one evidenced, two admitted guesses, one never
written down — and the code could not tell them apart, so all four got the same
behaviour and the same sentence. The fix is a second named set, so the reason a
backend is skipped becomes a thing a test can check.
The other one: a command list is not a capability list. opencode advertises no
compaction command and serves
/compactanyway. Absence of a flag is evidenceonly when the flag could have been there.