The token-meter projections now subtract compact/summary's
shadowedTokenCount verbatim, so the seeded-history fixture's hand-picked
10k count drove the message figure negative and killed the projections
baseline. Realize the seed first (realizeSeedFixture, idempotent, shared
with seedSession) and derive the count from the shadowed rows through
the composed meter, reproducing the previous per-node fold bit for bit —
the recorded aria goldens pass unchanged.
Fixture-authored content is the closed base vocabulary, so after the
text/reasoning/tool-call arms only tool-result remains; the literal
comparison and its JSON fallback were dead and failed oxlint.
A defined fold claim is always freshly built and adjacent metering events
cannot repeat, so presence alone decides the claim transition; the value
comparison was unreachable and failed the per-file branch gate.
The contextBreakdown and contextPressure units carried the full priced
surface, so each session's persisted projection checkpoint grew without
bound. A surface replacement is now priced by the shadow-price event
logged directly before it — compact/summary for compaction, the new
compact/prune from tool-result pruning (priced through the injected
token meter) — and the unit states shrink to a fixed handful of numbers.
Regenerate the persistence/cordis/module/config catalogs.
The claimed-message refactor changed Inbox.claim(target, turn) and added
InboxNotifications.claimed, so the cordis_inspect tool output embedded in
the cordis-inspect-jsdoc replay fixture now carries the new declarations.
Move the claimed-message notification loop out of the loop's pre-step
into Inbox.claim(target, turn), so the step-boundary operation publishes
its own claimed notifications like insertions and discards do.
The TTFT and tok/s readings divide by measured wall time, so they are not
reproducible: the same replayed scenario yielded 69 and 70 tok/s on
consecutive local runs, and a 3 ms replayed stream reads 26333 tok/s. Baking
those into committed goldens made the Web lane flaky by construction, and the
goldens for the readings themselves were never refreshed.
Three fixes, then a refresh:
The footer's decorative dots are `aria-hidden`, so the readings concatenated
into one accessible string — `Ran for 13sTTFT 0.2s12 tok/s`. That is a real
defect on its own (a reader hears one run-on instead of three facts) and it
also denied `{{duration}}` the word boundary it matches on, so even the
previously-stable `Ran for` duration started leaking raw. The separators now
carry flanking spaces.
`normalizeAria` gains `{{throughput}}` beside `{{duration}}`, and its duration
alternation accepts the stats line's compact `2m42s` as well as the
message-chrome template's `2m 42s` — the compact form had no pattern at all,
which is why `LLM 382m39s` survived the first refresh.
Refreshed 17 goldens. They also record that the stats line's `LLM` group now
renders at all: it folds assistant `timing`, which the live transcript adapter
only began attaching in this branch, so the group was previously dead in Chat.
Verified by running the lane in replay three times after the refresh: 41/41
files green each time, goldens untouched. Before this change two consecutive
runs disagreed on both the values and the failure count.
The merge staged the `--ours` consistency records before the merged prose was
re-recorded, so the committed hashes still describe the pre-merge content and
`verify-translation-pairing` rejects the pair. Re-record all three against
what actually merged.
The composer ring, percentage, and `~used / capacity` header read
`contextPressure.pressureTokens`, which moves only when a request reports
usage. Compaction reports none — compact-basic summarizes through a direct
`ctx.llm.stream()` call and appends only its own `compact/*` records plus the
replacement `user/message` — so the meter was frozen across the one action
taken to change it. Driving a real `compactNow` through the agent loop:
BEFORE compact: ring=4% header=~4227/100000 rows=[18, 0, 4365]
AFTER compact: ring=4% header=~4227/100000 rows=[18, 0, 286]
The composition rows fell 93%; the ring did not move, and would not until an
entire further turn completed. The panel then contradicted itself by more than
an order of magnitude at exactly the moment a reader opens it.
`contextPressure` now also publishes `projectedTokens`: the provider sample
plus the heuristic repricing of everything the surface gained or lost since
that sample, clamped at zero, folded through the shared `surface-fold.ts`. The
sample is stamped before the same event joins the surface, so an
`assistant/message` anchors against the surface its own request carried. Only
the delta is estimated, so the figure stays provider-anchored — the estimator's
CJK and JSON-schema underpricing stays out of the occupancy number — while
reacting the moment content lands or a span is shadowed. Same run after:
BEFORE compact: ring=4% header=~4323/100000 (pressure=4227, projected=4323)
AFTER compact: ring=0% header=~ 244/100000 (pressure=4227, projected= 244)
`contextOccupancy` prefers the projected figure and falls back to the bare
sample, so a projection restored from a pre-field checkpoint degrades to the
old behavior rather than disappearing. `stateVersion` moves to 3.
Drop the details-panel Duration toggle: Duration rows always show
integer milliseconds, matching the cell time column. Timeline labels
(Total/TTFT/Decoding) and step-group descriptions previously fell back
to second labels at or above one second; they now also show exact
milliseconds via the shared formatDurationMillis formatter.
`contextBreakdown.messageTokens` and `measure().surfaceTokens` answer the same
question in the same heuristic vocabulary, and the panel's composition rows are
only honest while they agree. Each owner carried its own copy of the positional
fold — same pricing, same `{seq, tokens}` node list, same replace-range lookup
and guard, differing only in mutable versus immutable application — so an edit
to either one would have moved the panel away from `measure()` with both sides
still green. The duplication gate caught the shared 62 tokens.
`src/surface-fold.ts` now owns `foldSurfaceTokens`: total, allocation-fresh,
returning the event's price, the next surface, and the signed total delta. The
service assigns that result where it used to prepare a commit closure, which
keeps its validate-before-mutate replay transaction intact — the fold throws
before any state is touched, so a malformed event still fails identically on
every retry. `_prepareSurfaceMutation` and `_estimateSurfaceEvent` go away with
it, and the projection's apply drops to one call.
Covers the identity with a session that appends and then compacts, asserting
the projection figure equals the service surface at each boundary; the test
fails when either side of the fold is perturbed.
The react-loop simplification folds the workspace baseline into the first
entering request, so the --dev CLI smoke no longer sees a workspace-free
probe request before the projected one. Resolve on the first provider request
and drop the obsolete no-workspace initial assertions.
imccyu
Huanqi Cao
_Kerman
fz
CreatixChu
creatixchu
Yichen Jiang
Turtle
Turtle