Two integration bugs found during review of #74522, both confirmed with
empirical probes against the production message-repair path:
1. Alternation: the summary marker was role="user" and an exchange was a
single assistant+tools group, so splicing between two user turns produced
user -> marker(user) -> user. The pre-request repair_message_sequence pass
(conversation_loop.py, runs before EVERY API call) then merged the marker
into the neighbouring real user message: metadata gone, cursor
unrecoverable on resume, and the summary text duplicated into the
transcript on every later pass (the transcript GREW every turn).
Fix: an exchange is now a full agent turn (assistant + tools + follow-up
assistant iterations, bounded by user messages), the marker is
assistant-role, and superseding an old marker deliberately merges the two
adjacent real user turns (plain-text \n\n-join, identical to repair
pass 2) so the returned transcript is alternation-valid by construction.
Probe result: repairs 0 (was 2), marker survives, no summary leakage.
2. Defrag destroyed user messages: _defrag_rolling_summary serialized the
whole remaining middle (user turns included) and spliced it away —
8 of 10 user prompts destroyed in one pass, contradicting the feature's
"your messages are never compacted" invariant. Fix: defrag now
re-summarizes only the rolling summary TEXT and rewrites the marker
content in place; transcript shape, cursor, and user turns untouched.
Probe result: 10 of 10 user prompts survive.
Also: marker provenance is now COMPRESSED_SUMMARY_HAS_USER_TURN_KEY=False —
micro markers absorb only assistant/tool content (#64650 invariant), and
real user turns remain in the transcript for provenance detection.
Adds 5 regression tests (repair-pass integration, alternation on
multi-iteration tool turns, defrag user survival, defrag input scope,
marker provenance); updates the two existing tests and the design doc to
the corrected semantics. 28 tests pass.
The on/off switch was the only knob. A pass fired after every completed turn,
absorbed exactly one exchange, and there was no way to ask for less. Since a
pass is also what breaks the prompt-cache prefix, "how often does it run" and
"how often do I pay a cache break" are the same question, and it had no answer.
Add `compression.micro_compact_every_n_turns` (default 1, clamped to >= 1). At 1
the behaviour is what it was; at 5 you get a fifth of the breaks and a fifth of
the reclaim rate. The counter advances per invocation rather than per committed
pass, so a turn that finds nothing to absorb still moves the cadence along and
cannot wedge it, and a bogus 0 or negative degrades to "every turn" instead of
silently disabling compaction.
Also expose `micro_compact_defrag_threshold_tokens`, which has been a hardcoded
attribute on the compressor with no path from config since it was added.
This does not give micro-compaction the prune's reclaim-size gate -- a pass
still commits whatever the single absorbed exchange saved. It makes the break
frequency tunable, which reaches the same end by absorbing less rather than by
waiting for a bigger win. The docs now say that plainly, including that a
reclaim threshold is the obvious follow-up and does not exist yet.
Tests cover the skip-until-due window, the cursor and prefix staying untouched
on skipped turns, the clamp, and that the feature is off unless enabled.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Review raised whether default-on can be reconciled with the prompt-cache
contract in AGENTS.md, which permits mutating past context only for context
compression and treats per-conversation caching as sacred. It cannot, and the
codebase already says so in its own words.
A micro-compaction pass rewrites already-sent history, so it invalidates the
cached prefix every turn rather than at an episodic boundary. That is the exact
cost the proactive prune gates against: `proactive_prune_min_reclaim_tokens`
exists, per its own config comment, to keep rewrites to "one big episodic break
instead of a tiny break every tool iteration." Micro-compaction has no
equivalent gate -- one exchange per turn means one break per turn, by design.
Default to off. An operator who wants the amortized stall can opt in with
`compression.micro_compact: true` and accept the tradeoff knowingly; nobody
inherits a per-turn cache break from installing an update.
Also register the key in config_defaults so it is discoverable and picked up by
the update path's new-options check -- it was previously read by agent_init but
declared nowhere -- and document the cache cost in docs/micro-compaction.md
instead of only the benefit. The measurements behind the feature (occupancy
plateau, zero batch compactions) never priced cache invalidation, and the doc
now says which numbers a reader would need to measure to justify enabling it.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Three corrections, all from measuring a real 3.5 hour session rather than
reasoning about the design.
"During the idle moment after a response" was wrong. A pass is a real call
to the compression model at the end of a turn: the answer has streamed, but
the turn does not close until it finishes. Measured 2 to 37 seconds, median
around 31, on a small local model. Say so.
Add the choice of `auxiliary.compression` model as its own section, because
it dominates everything else here. A pass sends only a few thousand tokens
but runs every turn, so latency is felt repeatedly, and reasoning models are
a poor fit -- merging one exchange into a summary is mechanical work, and a
thinking model spends reasoning tokens on it for no benefit. Two measured
data points are given as illustrations of the shape, explicitly not as
recommendations: the right answer depends on the operator's hardware.
Add what a working session actually looks like: occupancy climbing to ~22%
and flattening (equilibrium -- 4,841 tokens added between the last two
passes, 4,395 reclaimed), zero batch compactions, and reclamation only
ramping after the tail budget is crossed. Also state the cost in the same
breath rather than burying it.
Frame the feature as a tuning option rather than a win: it lets you choose
how the compression cost is distributed and which model pays it. It is not
a magic bullet and the docs should not imply otherwise.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Tokens saved is the wrong headline for this feature. Micro-compaction is
not an efficiency optimisation — the same summarization work happens either
way. What it buys is (a) that work amortized across turns instead of one
stall, and (b) a window kept low enough that a session runs much further
before needing a hard compaction at all.
Neither shows up in "net tokens saved". A session can save nothing on paper
and still be a clear win on both counts.
So the telemetry now carries occupancy: tokens_after as a share of the
compaction threshold, plus the threshold and resolved window it was
computed from. That is the number that says whether a session has headroom
left. The report leads with it, and cross-references the batch
`compression_attempt` lines already in the log so it can show how often the
long pause actually fired — ideally never.
Occupancy is read from the cached threshold only. The public
`threshold_tokens` property resolves lazily and can issue a synchronous
/models probe (#32221); telemetry must never be the thing that blocks a
turn, so an unresolved window reports null. In practice a pass has already
resolved it via the tail calculation, so the field is populated. A test
pins the no-forcing behaviour directly against the emitter.
The report is pure ASCII: `scripts/check_subprocess_stdin.py` currently
dies on a cp1252 console before printing its results, and a diagnostic tool
that crashes on the platform it is diagnosing is worse than no tool.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The existing log line reports message counts, which is the least
informative number available here: absorbing one tool-heavy exchange can
drop hundreds of tokens while moving the count by one. There was no way to
answer "is this actually helping?" from a real session.
Emit one content-free JSON line per pass, in the same shape as the batch
compaction telemetry: before/after tokens, the delta, the size of the
absorbed exchange, the rolling summary size, duration, and running
per-session totals so a whole run can be read off the last line. No
transcript content rides along.
Add scripts/micro_compaction_report.py to aggregate those lines into
passes, outcome mix, net tokens saved, mean exchange size and durations,
with an optional per-session breakdown.
Measuring it immediately surfaced something worth documenting: the first
pass in a session normally *costs* tokens. The summary marker carries a
fixed ~400 tokens of scaffolding, paid on pass one against a single
absorbed exchange. From pass two the marker is replaced rather than added,
so the overhead is already paid and each exchange is close to pure saving.
Break-even is typically the second or third pass. Tests cover the
telemetry contract, the cumulative totals, and that first-pass/later-pass
shape so nobody reads a single turn and concludes it made things worse.
The estimator costs ~5 ms at 600 messages and ~20 ms at 1200, taken twice
per pass, post-turn — and only once an exchange is actually in hand, so
turns that no-op early pay nothing.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
`_find_one_exchange`'s docstring described an exchange as "(optional) user
message + assistant message + its tool results", but the walk skips past
user messages and starts at the assistant, so user turns are never absorbed
into the rolling summary.
The code is right and the docstring was wrong. Assistant output is largely
an account of what was done and survives summarising with little loss. The
user's messages are the intent everything else is derived from and cannot be
reconstructed from the work that followed — paraphrasing "use the existing
helper, don't add a new one" into a summary is how an agent ends up doing
the opposite six turns later. They are also cheap: a prompt is normally a
tiny fraction of what one tool result costs.
Correct the docstring, document the property (and its cost — a floor on how
small the middle can get, since user turns accumulate), and add a test so it
stays deliberate.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Covers what it does, the head/tail protection, the cursor and rolling
summary, defrag, how the session DB is kept in step, and the failure
paths. States the tradeoff up front: compression cost is amortized across
turns, at the price of older detail becoming summarized earlier in a
session than batch-only compaction would.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
