* usage: the usage tests pass at any time of day, midnight included The usage tests stamped their calls with the machine's time and then asked for today, 7 or 30 days, or a cached answer, which the code worked out from its own time.Now a moment later. A minute after midnight a call made "a minute ago" was yesterday's, and when midnight fell between the test's read and the code's, the call and the period were of two days. magpie usage, the TUI's Usage page, the two Codex cache-write tests and the computers' shared days failed in the first minutes after midnight (the TUI's after midnight UTC, the zone its package's tests run in since1caea638), and 28 more failed when midnight fell inside them. usage.Clock is now the time every period is read by: the start of today, 7 days and 30 days (LedgerOf, Summarize, Direct, QueryPage), the hours or days of the chart (LedgerSeries, QueryPage), the day a cached summary or page is for, the time Append gives a call that has none, the days davsync shares and the date in an exported CSV's name. It is time.Now, as before, and a variable for the tests, like LogCalls. Each test that built its calls from the time now holds Clock at noon on 2026-09-30 (holdClock; holdUsageClock in gui and the CLI; three lines in tui and davsync) and stamps its calls from that instant, among them TestReasoningReplyTimedByItsAnswer, whose timeline rows117b6c7fmade at time.Now. TestPeriodsReadTheClock checks that every one of these reads goes through Clock. TestQueryPageSourceAndIdentityInvalidation is held too; that it fails when run alone is fixed apart from this, in #1045. Seven held tests could not fail at midnight before, and are held so that the tests read one clock: TestUsageSameSizeAndMtimeRewrite (All's totals), TestDirectCountsOnlySessionFileCalls (30 days around its own noon), TestQueryPageIOOutsideCacheLock (a file two days old), gui's TestUsageLedgerDayRoutes (7 days hold its calls from either day), TestLedgerSingleSnapshotAndLocalSession and TestLedgerNamesModelAtProvider (their calls are stamped after the code reads the time), and TestUsageRawAndPricedChunksShareBudget, which fails only when the midnight in it starts a new week of All's chart, on a Sunday night; at.sh sets the time of day and not the weekday, so that one was not shown. Verified with at.sh, a scratch script that runs a test binary under a zone made with zic, so that the local time of day is the one asked for as the run starts (HOME in a sandbox, Go's caches pinned). The runs were first made onc5a54bc7, and those marked (698da36f) again on698da36f, with the same results. The tui package runs in UTC since1caea638, a zone at.sh doesn't move, so its runs on698da36fused copies of both trees whose TestMain keeps the zone TZ sets. Before, at 00:00:30, 00:01:30 and 12:00:00 (698da36f): TestUsageShowsCallsNotThroughMagpie, 00:00:30: usage_cli_test.go:95: no calls today · route an agent through magpie and its usage shows up here 00:01:30: "5 tokens today · 1 call · no price", without the calls not through magpie; TestUsagePageShowsCallsNotThroughMagpie (tui) fails the same two ways at usage_test.go:138 --- FAIL: TestCodexCacheWriteNotInInput (00:00:30) codex_cache_write_test.go:104: rows [] --- FAIL: TestCodexCacheWriteMatchesGatewayCall (00:01:30) codex_cache_write_test.go:73: filter {...}: 0 rows, 0 calls, want the gateway's 2: [] --- FAIL: TestUsageSharedBetweenComputers (00:01:30) usage_share_test.go:134: a's days on the server: [...-2026-10-05 ...-2026-10-06 ...-2026-10-07] 12:00:00: PASS Midnight inside a test, in scratch copies of the head. Started at 23:59:59.3 with the code's first period read held 1.5s, so that it reads after midnight what the test stamped before it, 16 usage tests, 3 gui tests and TestUsageCSV FAIL, among them ledger_test.go:257: today: 0 review_test.go:69: chart counted 0 incremental_log_test.go:202: concurrent append lost TestCachedSummaryRemainsCallerOwned: panic: runtime error: index out of range [0] with length 0 usage_test.go:121: second page: {... Period:today Rows:[] ... Total:0 ...} usage_test.go:311: "": magpie-requests-7d-2026-10-06 Started at 23:59:55 with the test waiting past midnight between two of its reads, 7 more FAIL: request_day_test.go:45: selecting a day changed the chart or its legend cache_bounds_test.go:84: uncached today summary stale growing_rewrite_test.go:71: today summary stale cache_bounds_test.go:153: page key changed instead of exercising the same cache priced_blocks_test.go:55, caller_provider_test.go:129 and :172: page differs TestReasoningReplyTimedByItsAnswer, with a scratch 1.5s sleep before its LedgerSeries, started at 23:59:59.3 (698da36f): usage_test.go:255: part: {Calls:0 Tokens:0 Cost:0 Timed:0 TTFT:0 DecodeMs:0 DecodeOut:0} After: the same at.sh runs PASS at 00:00:30, 00:01:30 and 12:00:00 (698da36f); the same scratch copies made of this change PASS, each test taking 1.5s or 5.2s, so midnight did fall inside it (698da36ffor TestReasoningReplyTimedByItsAnswer's); and every changed test PASS at 23:59:59.9, 00:00:30 and 12:00:00 (698da36f). Without the change (698da36f): with the reads put back on time.Now, 21 usage tests, 6 gui, 2 CLI, the tui and the davsync test fail, among them --- FAIL: TestPeriodsReadTheClock clock_test.go:55: Direct(Today): 0 calls since 2026-10-06 00:00:00 -0700 PDT, want 1 since 2026-09-30 00:00:00 -0700 PDT clock_test.go:63: Summarize(Today) the next day: 1 calls, want 0 --- FAIL: TestReasoningReplyTimedByItsAnswer usage_test.go:255: part: {Calls:0 Tokens:0 ...} Each of the eleven reads put back alone fails a test: TestPeriodsReadTheClock for the nine in usage (LedgerSeries: "clock_test.go:52: LedgerSeries(Today): 0 calls, want 2"; the page's cache key: "clock_test.go:66: QueryPage(Today) the next day: 1 rows, want 0"), TestCSVStamp for the CSV's name (usage_test.go:325: "": magpie-requests-7d-2026-10-06) and TestUsageSharedBetweenComputers for davsync (usage_share_test.go:224: all computers: 4 rows, 707 in; want 5, 737). On this commit: go test -tags nogui -count=1 . ./internal/usage ./internal/tui ./internal/davsync ./internal/gui ok; -race -count=20 over the changed tests of each of these packages ok; gofmt -l prints nothing, and go vet -tags nogui on the five packages finds nothing. * usage: pages, CSVs and magpie usage asked at midnight show one day An answer about usage read the time more than once. The Requests page read it for the day it is kept for, for the period its log and session files are read over, for the period of its rows and for its chart's hours; the page from the ledger (QueryPage's path when LogCalls is set, as in the tests) for its rows and for its chart; Direct for its period and for its rows; a CSV for its rows and for its name; magpie usage and the TUI's Usage page for Summarize and then for Direct. Most of these reads have the log and the session files read between them, seconds on a large log, and when midnight fell between two of them the answer was of two days: yesterday's calls listed over today's empty chart, Direct starting yesterday and counting none of yesterday's calls, the calls not through magpie left out of magpie usage and the Usage page (they were the new day's, none yet), and yesterday's calls saved as magpie-requests-today-<the new day>.csv. Each answer now reads Clock once and passes that moment down. queryPage reads it for its key, its sources, its rows and its chart (buildRequestBlocks takes it); the page from the ledger reads its rows and its chart at it (LedgerOfAt, ledgerSeriesAt); Direct reads the ledger at the moment of its period. usage.Summaries(p) is Summarize(p) and Direct(p) at one moment, and magpie usage and the TUI's Usage page, when a period is picked and when it is read again, ask for it: one exported name, the clock left inside usage and one line changed at each caller, where SummarizeAt and DirectAt would be two names and each caller would read the clock itself. The CSV download and export read their rows with the new usage.LedgerOfAt at the moment their file is named for, which csvStamp now takes; the rows and the name are read in two packages, so LedgerOfAt is exported. LedgerOf, LedgerSeries, Summarize, Direct and QueryPage keep their signatures, each reading Clock once. The new tests set Clock to read a tenth of a second before midnight the first time and a tenth of a second after it from then on, set again for each answer. The midnight is the one that starts 2026-10-01, local time: a past instant, at midnight because that is what is tested, and the day before it is the 2026-09-30 the held tests use. TestAnswerReadsTheClockOnce asks QueryPage(Today) from the indexed log and from the ledger: its 3 rows, one from a session file written that day at 23:00, are under that day's chart, and asked again after midnight the page is the next day's, not the one kept for the day before; Direct(Today) counts the call and starts that day. TestUsageAskedAtMidnight (magpie usage today), TestUsagePageAtMidnight (the TUI's Usage page, today picked and read again) and TestUsageCSVAtMidnight (download and export) check that the calls through magpie and those not through it, or the rows and the file's name, are of the day asked on. TestCSVStamp passes its time. Verified on the previous commit, at.sh as there. The runs were first made onc5a54bc7, when the tui package's tests still ran in the local zone, and those marked (698da36f) again on698da36f, with the same results. Before: the new tests on the previous commit, at any time of day (at.sh at 12:00:00 too) (698da36f): --- FAIL: TestAnswerReadsTheClockOnce clock_test.go:131: QueryPage(Today): 0 rows, 0 in a chart from 2026-10-01 00:00:00 -0700 PDT; want 3 under one from 2026-09-30 00:00:00 -0700 PDT clock_test.go:141: QueryPage(Today): 3 rows, 0 in a chart from 2026-10-01 ...; want 3 under one from 2026-09-30 ... clock_test.go:145: Direct(Today): 0 calls since 2026-09-30 00:00:00 -0700 PDT, want 1 since 2026-09-30 00:00:00 -0700 PDT --- FAIL: TestUsageAskedAtMidnight usage_cli_test.go:154: 5 tokens today · 1 call · no price ..., with no part for the calls not through magpie --- FAIL: TestUsagePageAtMidnight usage_test.go:184: today picked: ... (the same) usage_test.go:187: read again: ... --- FAIL: TestUsageCSVAtMidnight usage_test.go:367: download: 200, attachment; filename="magpie-requests-today-2026-10-01.csv" with 2 rows (<nil>), want magpie-requests-today-2026-09-30.csv with 2 usage_test.go:378: export: 200 {"path":"~/Downloads/magpie-requests-today-2026-10-01.csv", "rows":1}, want magpie-requests-today-2026-09-30.csv with 1 row With the real clock, in scratch copies of both trees: scratch tests held one of Clock's reads 1.5s after it was made, as reading a large log does (the first; for one of them the page's third, its chart's), and at.sh started each at 23:59:59.3. Before, all 9 FAIL, among them asked 23:59:59.564, answered 00:00:01.068 Direct(Today): 0 calls since 2026-10-05 00:00:00 -0940 MID, want 1 since 2026-10-05 00:00:00 -0940 MID QueryPage(Today): 2 rows, 0 in a chart from 2026-10-06 ...; want 2 under one from 2026-10-05 ... download: attachment; filename="magpie-requests-today-2026-10-06.csv" with a call of 2026-10-05 23:59 After, all 9 PASS, answered at 00:00:00.9 to 00:00:01.0, so midnight fell inside each, except the chart's: its held read is gone with the change. A scratch sleep before the chart shows that one: before "2 rows, 0 in a chart from 2026-10-06", after PASS, asked 23:59:59.344 and answered 00:00:00.941. At 12:00:00 all of them PASS in both trees. After: every changed test PASS with at.sh at 23:59:59.9, 00:00:30 and 12:00:00 (698da36f). Without the change (698da36f): with the production put back to the previous commit's (gui/usage.go only so far that TestCSVStamp compiles: csvStamp takes the time, read apart from the rows as before), go test -count=1 . ./internal/usage ./internal/tui ./internal/gui fails the four new tests and no other, with the lines above. Each of the 16 places put back alone fails one of them: the page's key (clock_test.go:134: "3 rows, 3 in a chart from 2026-09-30 ...; want 0 under one from 2026-10-01 ..."), its sources (:131: "2 rows"), its rows (:131: "0 rows"), its chart (:131), the ledger page's rows and chart (:141), LedgerOfAt (:141, :145), ledgerSeriesAt (:141), Direct (:145); Summaries, indexedSummary and magpie usage (usage_cli_test.go:154); Summaries and the TUI's period key and reload (usage_test.go:184, :187); the CSV's download and export (usage_test.go:367, :378). On this commit: go test -tags nogui -count=1 . ./internal/usage ./internal/gui ./internal/tui ./internal/davsync ./internal/gateway ok; -race -count=20 over the changed tests of each package ok; gofmt -l prints nothing, and go vet -tags nogui finds nothing. * gateway: the key-limit tests pass when a run crosses local midnight A go test run that crossed local midnight could fail the gateway's key-limit tests. keyLimited and the /v1/magpie/limit endpoint each read time.Now() when they check a key, and access.Window turns that into a calendar window (a day from midnight, a week from Monday, a month from the 1st). The tests seed "yesterday" from their own time.Now() and then make several calls, so a run that crossed midnight saw its calls split over two windows: the second call of a 350-token day was let in, or a restart counted nothing. The gateway's key-limit path now reads limitClock, a variable for the tests like ruleClock and idClock, and production behaviour is unchanged (it is time.Now). TestKeyLimitRefusesBeforeUpstream, TestKeyLimitHoldsParallelRequests and TestKeyLimitWindowResets pin it at 2026-09-30 12:00 local and seed "yesterday" from that instant. Calls are still recorded at the real time, after the pinned one, and a window counts every call from its start, so they all count in the pinned window; the "tomorrow's window" check in TestKeyLimitWindowResets stays on the real now, the first window with none of those calls in it. No other test sets a key limit with records in its window (the gateway-key CLI test and the GUI caller-key tests count 0 calls or have no limit). TestKeyLimitRefusesBeforeUpstream now also checks that the 429's Retry-After and X-Magpie-Limit-Reset name the next midnight after the check, and that the limit endpoint's week starts on the pinned Monday. Verified with at.sh, a scratch script that runs the test binary under a zone made with zic, so that the local time of day is the one asked for as the run starts: - before, at.sh at 23:59:59 with COUNT=500/300 and FRAC 0.3/0.6/0.8: 3 of 6 runs of each test failed with key_limit_test.go:217: spent key let in key_limit_test.go:117: a restart forgot what the key used 200 key_limit_test.go:121: status &{Period:day Start:2026-10-06 ... Calls:0 Tokens:0 ...} - after, the same 6 runs (COUNT=500, both tests) print PASS, and so do ^TestKeyLimit at 12:00:00 and 00:00:00 with COUNT=20. - go test -tags nogui -count=1 ./internal/gateway: ok (79.5s); -race -count=20 -run '^TestKeyLimit' ./internal/gateway: ok. - gofmt -l prints nothing; go vet -tags nogui ./internal/gateway is clean. The month boundary (TestKeyLimitHoldsParallelRequests) and Monday can't be reproduced by changing the time of day; the pinned clock covers them the same way. Fails without the change (tests pinned, keyLimited back on time.Now): --- FAIL: TestKeyLimitRefusesBeforeUpstream key_limit_test.go:107: headers map[... Retry-After:[80228] X-Magpie-Limit-Reset:[2026-10-07T00:00:00-07:00] ...] and with only the limit endpoint back on time.Now: --- FAIL: TestKeyLimitRefusesBeforeUpstream key_limit_test.go:159: limit endpoint {... "period":"week", "start":"2026-10-05T00:00:00-07:00" ...} * gateway: the routing history tests pass when a run crosses midnight TestHistoryKeepsDaysAndDropsOld and TestRemoteMagpieGroupHistory took now := time.Now() and saved routes at now and now+1s. saveRoute files a route by its own day (r.Time.Local()), so a test started at 23:59:59 put the +1s route in tomorrow's file and History(today) found one route less. TestHistoryKeepsSessionAndTokenTiers raced the other clock: saveRoute prunes by time.Now(), so when the day turned between the test's time.Now() and the first saveRoute, the prune gzipped "today" after the first route, the second went to a new .jsonl, and the test's own pruneHistory gzipped that over the first .gz, losing route 1. saveRoute now prunes by historyClock (time.Now outside the tests). The three tests take historyNoon(t), which holds that clock at 2026-09-30 12:00 local and returns it as their now, restored with t.Cleanup. Every route, day file and prune is then on that one past day. The fixture can't be a fixed past day without the clock: pruning by the real today gzips that day's file at once (and, a month on, drops it as too old). The other history tests keep the real clock: TestHistoryRouteOutsideDayLimit writes its day files itself from one now and the code under test reads no clock, and TestHistoryRouteDayAndNoLock already uses a fixed day. Verified with at.sh, a scratch script that sets the local time of day through a zone made with zic as the run starts: - before, at.sh ./internal/gateway at 23:59:59: --- FAIL: TestHistoryKeepsDaysAndDropsOld history_test.go:50: days [{2026-10-06 1} {2026-10-05 1} {2026-10-04 1}] --- FAIL: TestRemoteMagpieGroupHistory remote_group_served_test.go:144: routes [... only ID 1 ...] and, with a 2s sleep after now := time.Now() standing in for the turn of the day, --- FAIL: TestHistoryKeepsSessionAndTokenTiers history_test.go:22: compressed history lost accounting: [only ID 2] 12:00:00 control: PASS. - after: the three tests PASS at 23:59:59, 23:59:59.9 (FRAC=0.9), 12:00:00, and 23:59:59 with the same 2s sleep; all TestHistory* and TestRemoteMagpieGroupHistory PASS at 23:59:59 with -test.count=3. - with saveRoute pruning by time.Now() again (the fixtures still pinned), at any time of day: --- FAIL: TestHistoryKeepsSessionAndTokenTiers history_test.go:32: compressed history lost accounting: [only ID 2] - go test -tags nogui -count=1 ./internal/gateway: ok; -race -count=20 on the three tests: ok; gofmt -l and go vet -tags nogui ./internal/gateway print nothing. * gateway, davsync: the request archive tests pass when a run crosses UTC midnight The archive names a call "<date>/<id>" from the call's own start, in UTC (archiving in archive.go). TestArchiveOn read time.Now().UTC() before posting and TestRequestArchiveToS3 read it before post(), and each expected that read's date. A run where UTC midnight (17:00 PDT) fell between the test's read and the request's start expected the day before the one the archive used, and failed. Both tests now take the date from the Time the call carries (s.Recent()[0].Time, the same start the archive's name is made from), in UTC, so nothing is read from the clock a second time. No production code changes. The other archive tests already go by the call's Archive name, and internal/gui's archive test uses a fixed name; no other test in internal/gateway, internal/davsync or internal/gui predicts an archive key or a UTC-dated name from its own clock. Verified: at.sh only moves the local time of day, and this is a UTC crossing (UTC midnight was ~16h away), so it was shown in a scratch copy whose serve starts each request 0.2s after the next UTC midnight, as a request does when the test read the clock just before it. There the old tests fail: archive_test.go:115: call archive "2026-10-07/000000-f4690de23ee8a859", want "2026-10-06/000000-f4690de23ee8a859" archive_test.go:93: nothing at "team x+y/magpie/archive/2026-10-06/000000-0e74a87816ef6a56.json" and the new ones pass. Unshifted, under at.sh at local 23:59:59, 00:00:00 and 12:00:00, both pass, as the old ones do at 23:59:59 and 00:00:00 (local time doesn't enter the name). With archiving naming by start.Format (local) instead of start.UTC().Format, both new tests fail under at.sh at local 23:00:00, where the local date is a day behind UTC's: --- FAIL: TestArchiveOn ... archive_test.go:116: call archive "2026-10-05/082500-7322712bd89f71da", want "2026-10-06/082500-7322712bd89f71da" --- FAIL: TestRequestArchiveToS3 ... archive_test.go:95: nothing at "team x+y/magpie/archive/2026-10-06/082500-3587ab4192da2cd5.json" and pass at 12:00:00. go test -tags nogui -count=1 ./internal/gateway ./internal/davsync passes in a sandbox HOME; -race -count=20 -run '^(TestArchiveOn|TestRequestArchiveToS3)$' passes; gofmt -l and go vet -tags nogui on both packages are clean. * gui: TestWhatsNewTodayRoute passes when the run crosses local midnight TestWhatsNewTodayRoute posts {"on":true} to /api/whatsnew/today, which writes today() to whatsnew-quiet-day, then checks quietToday(), which compares the file with a second today(). A run that crossed local midnight between the two read different days and failed with "on: 204 false". The neighbouring TestWhatsNewQuietAfterRestartToUpdate already pins today; this test didn't. The test now pins today to 2026-09-30 (restored with t.Cleanup), so the post and the check read the same day. The other What's new tests start from an empty folder, so quietToday finds no file and never reads today(). Verified: with a temporary 1s sleep between the post and the check, the unpinned test under at.sh (local time of day set by a zone) started at local 23:59:59.5 failed with "whatsnew_test.go:237: on: 204 false" and passed at 12:00:00; pinned, it passes at 23:59:59.5 (same sleep), and, without the sleep, at 23:59:59, 00:00:00 and 12:00:00. With setQuietToday writing time.Now().Format("2006-01-02") instead of today(), the test fails: "--- FAIL: TestWhatsNewTodayRoute ... whatsnew_test.go:239: on: 204 false". go test -tags nogui -count=1 ./internal/gui passes in a sandbox HOME; -race -count=20 -run '^TestWhatsNewTodayRoute$' passes; gofmt -l and go vet -tags nogui ./internal/gui are clean. * provider: TestZCodeStartSentAsTheApp passes when the run crosses midnight A ZCode Start Plan request opens with a context prefix that says "Today's date is <day>" (zcodeDateReminder), the day zcodeStartRequest took from its own time.Now(). TestZCodeStartSentAsTheApp sent the request, then built the expected prefix from a second time.Now(). A run that crossed midnight between the two failed on "the context prefix", the request holding the day before. zcodeStartRequest now takes the time from zcodeClock (a package variable, time.Now outside tests, as gateway's ruleClock), and the test pins it to 2026-09-30 12:00 local, restored with t.Cleanup, and expects "Today's date is 2026-09-30." The test sets TZ=Asia/Shanghai, which moves time.Local only when nothing has read it yet; a mid-day instant in time.Local formats to the same day either way. The other calls to zcodeStartBody in the test check shaping only, not the day. No other provider test builds a day string from a second clock: the WorkBuddy credits, daily warm-up and check-in tests pass fixed times to code that takes now as an argument, and TestQoderCheckinOnTheCard's day is only carried, not compared. Verified with at.sh (local time of day set by a zone, run as -run '^(TestDailyCredits|TestZCodeStartSentAsTheApp)$' so that time.Local is read before the test's t.Setenv("TZ"), as in a full run; alone, Local becomes Asia/Shanghai): with a temporary 1s sleep after the request, the unpinned test started at local 23:59:59.5 failed with "zcode_client_test.go:195: the context prefix: ... Today's date is 2026-10-05." and passed at 12:00:00; pinned, it passes at 23:59:59.5 (same sleep) and, without the sleep, at 23:59:59, 00:00:00 and 12:00:00. With zcodeStartRequest back on time.Now(), the pinned test fails: "--- FAIL: TestZCodeStartSentAsTheApp ... zcode_client_test.go:196: the context prefix: ... Today's date is 2026-10-06." go test -tags nogui -count=1 ./internal/provider passes in a sandbox HOME; -race -count=20 -run '^TestZCodeStartSentAsTheApp$' passes; gofmt -l and go vet -tags nogui ./internal/provider are clean. * accounts, quota: a window's reset reads against one time per listing; TestQuotaCell passes across midnight quotaCell, a window in `magpie accounts` and `magpie quota`, read the clock three times: whether the reset had passed, how long until it, and ResetClock's label, which names the calendar day ("tomorrow 02:13" or "02:13"). TestQuotaCell set the reset 2h13m30s from time.Now() and built the expected label from yet another time.Now(); a run that crossed local midnight between quotaCell's read and the test's got "tomorrow 02:13" from one and "02:13" from the other and failed. quotaCell now takes now. accountsCmd and quotaCmd take one time.Now() just before printing and pass it to every window's cell, so a listing's windows agree on what "today" is. The test passes a fixed 2026-09-30 12:00 local and expects "↻2h13m 14:13", and for a reset the next day "↻14h13m tomorrow 02:13"; no zone in tzdata 2026c changes its clock between those instants, so both read the same in any TZ. resetsCell's label, quotaReadingCell's expired check and quotaResetCmd's prompt still read time.Now(); no test compares them against a second clock. internal/tui's quotaCell and quotaLines already take now, and their tests pass a fixed one. Verified with at.sh (local time of day set by a zone): with a temporary 1s sleep between quotaCell and the check, the old test started at local 23:59:59.5 failed with "accounts_cli_test.go:128: \"5h 42% ↻2h13m tomorrow 02:13\"" and passed at 12:00:00; the new one passes at 23:59:59.5 (same sleep) and, without the sleep, at 23:59:59, 00:00:00 and 12:00:00. Putting any of quotaCell's three reads back on the wall clock fails the test ("--- FAIL: TestQuotaCell"). ResetClock's now alone fails the next-day case: "accounts_cli_test.go:134: tomorrow: \"7d 42% ↻14h13m 02:13\"". The passed check alone, or all three: "accounts_cli_test.go:129: \"5h 42% · reset time passed Sep 30 14:13\"". untilShort alone: "accounts_cli_test.go:129: \"5h 42% ↻now 14:13\"". go test -tags nogui -count=1 . passes in a sandbox HOME; -race -count=20 -run '^TestQuotaCell$' passes; gofmt -l and go vet -tags nogui . are clean.
744 lines
25 KiB
Go
744 lines
25 KiB
Go
package usage
|
|
|
|
// The ledger: every call of a period, one row each, newest first — what
|
|
// the agent asked for, where it went, what model answered, the tokens and
|
|
// what they cost at the effective price — to set beside a vendor's own bill.
|
|
|
|
import (
|
|
"encoding/csv"
|
|
"io"
|
|
"slices"
|
|
"sort"
|
|
"strconv"
|
|
"strings"
|
|
"time"
|
|
|
|
"github.com/yetone/magpie/internal/catalog"
|
|
"github.com/yetone/magpie/internal/provider"
|
|
"github.com/yetone/magpie/internal/sessions"
|
|
"github.com/yetone/magpie/internal/settings"
|
|
)
|
|
|
|
// Row is one call as the ledger lists it.
|
|
type Row struct {
|
|
Record
|
|
// Cost is the call's effective price in USD, when its model's is known
|
|
// (Priced); Swapped: the reply named another model than Model
|
|
Cost float64 `json:"cost"`
|
|
Priced bool `json:"priced"`
|
|
Swapped bool `json:"swapped,omitempty"`
|
|
// Routed marks a remote magpie group answered by one of its members.
|
|
Routed bool `json:"routed,omitempty"`
|
|
// Source is "log" for a call read from an agent's own session file,
|
|
// which the gateway never saw: no status, no provider, no model asked
|
|
// for, but what the file says of the call. "" for one the gateway logged.
|
|
Source string `json:"source,omitempty"`
|
|
}
|
|
|
|
// Failed is whether the call failed: the agent was answered an error status,
|
|
// or, for a call read from a session file, which has no status, the file
|
|
// says an error ended it.
|
|
func (r Record) Failed() bool { return r.Status >= 400 || r.Error != "" }
|
|
|
|
// Filter narrows the ledger: to a route, one agent (its id, as AgentOf gives it), to
|
|
// one provider, to the failed calls, and to the rows whose models, provider, host or
|
|
// session hold Query (any case).
|
|
type Filter struct {
|
|
Day string // YYYY-MM-DD in the chart's local time zone; "" is the whole period
|
|
CallerKey string
|
|
RouteID int64
|
|
Model string // exact model selected in the ranking
|
|
Agent string
|
|
Provider string // a provider's id, as the ledger's rows have it
|
|
Purpose string // PurposeOf's key; empty keeps every purpose
|
|
// Account narrows to the calls a subscription account answered, by its
|
|
// name as Record.Account gives it (#557)
|
|
Account string
|
|
Failed bool
|
|
Query string
|
|
// Computer narrows to the calls of one computer (#542): ThisComputer,
|
|
// OtherComputers, or another's id; "" is every computer's
|
|
Computer string
|
|
}
|
|
|
|
// OtherComputers is the Filter.Computer of every other computer's calls.
|
|
const OtherComputers = "others"
|
|
|
|
// computer is whether r is of the computers Computer picks.
|
|
func (f Filter) computer(r Record) bool {
|
|
switch f.Computer {
|
|
case "":
|
|
return true
|
|
case ThisComputer:
|
|
return r.Computer == ""
|
|
case OtherComputers:
|
|
return r.Computer != ""
|
|
}
|
|
return r.Computer == f.Computer
|
|
}
|
|
|
|
func (f Filter) keeps(r Record) bool {
|
|
if f.Day != "" && r.Time.In(time.Local).Format(time.DateOnly) != f.Day {
|
|
return false
|
|
}
|
|
if f.CallerKey != "" && r.CallerKeyID != f.CallerKey {
|
|
return false
|
|
}
|
|
if f.RouteID != 0 && r.RouteID != f.RouteID {
|
|
return false
|
|
}
|
|
if f.Model != "" && r.Model != f.Model {
|
|
return false
|
|
}
|
|
if f.Agent != "" && AgentOf(r.Agent) != f.Agent {
|
|
return false
|
|
}
|
|
if f.Provider != "" && r.Provider != f.Provider {
|
|
return false
|
|
}
|
|
if f.Purpose != "" && PurposeOf(r.Kind) != f.Purpose {
|
|
return false
|
|
}
|
|
if f.Account != "" && r.Account() != f.Account {
|
|
return false
|
|
}
|
|
if !f.computer(r) {
|
|
return false
|
|
}
|
|
if f.Failed && !r.Failed() {
|
|
return false
|
|
}
|
|
if q := strings.ToLower(strings.TrimSpace(f.Query)); q != "" {
|
|
return slices.ContainsFunc([]string{r.Requested, r.Model, r.Served, r.Upstream, r.Provider, r.Host, r.Session, r.Effort, r.SessionProvider, r.SessionAccount, r.ProviderKeyID, r.ProviderKeyName, r.Account(), r.CallerKeyID, r.CallerKeyName}, func(s string) bool {
|
|
return strings.Contains(strings.ToLower(s), q)
|
|
})
|
|
}
|
|
return true
|
|
}
|
|
|
|
// Since is when the period began, as of now; zero for all.
|
|
func (p Period) Since(now time.Time) time.Time {
|
|
day := time.Date(now.Year(), now.Month(), now.Day(), 0, 0, 0, 0, now.Location())
|
|
switch p {
|
|
case Today:
|
|
return day
|
|
case Week:
|
|
return day.AddDate(0, 0, -6)
|
|
case Month:
|
|
return day.AddDate(0, 0, -29)
|
|
}
|
|
return time.Time{}
|
|
}
|
|
|
|
// LogCalls reads the calls the agents' own session files record, which the
|
|
// ledger adds to those the gateway logged. A variable for the tests.
|
|
var LogCalls func(time.Time) []sessions.Call
|
|
|
|
// Clock is the time the periods are read by: when today began, the hours
|
|
// or days of the chart, the day a cached answer is for. A variable for the
|
|
// tests, which hold it still so that midnight never falls between a call
|
|
// they log and the period they ask for.
|
|
var Clock = time.Now
|
|
|
|
// Ledgered is a period's calls that a filter keeps, newest first, with their
|
|
// sum, and the agents and providers that made any call in the period (their
|
|
// ids, for a filter to offer).
|
|
type Ledgered struct {
|
|
Rows []Row
|
|
Sum Totals
|
|
Agents []string
|
|
Providers []string
|
|
}
|
|
|
|
// LedgerOf is the calls of a period that the filter keeps. The gateway's log
|
|
// comes with the calls the agents' session files record that the gateway did
|
|
// not see.
|
|
func LedgerOf(p Period, f Filter) Ledgered {
|
|
return LedgerOfAt(p, f, Clock())
|
|
}
|
|
|
|
// LedgerOfAt is LedgerOf with the period read at now, for an answer that
|
|
// names that moment elsewhere too, as an exported CSV's name does.
|
|
func LedgerOfAt(p Period, f Filter, now time.Time) Ledgered {
|
|
since := p.Since(now)
|
|
gatewaySince := since
|
|
if !since.IsZero() {
|
|
gatewaySince = since.Add(-24 * time.Hour)
|
|
} // calls ending across the period boundary
|
|
reader := LogCalls
|
|
if reader == nil {
|
|
reader = sessions.Calls
|
|
}
|
|
rows, sum, agents, providers := ledgerWithShared(since, f, Load(gatewaySince), reader(since), sharedRecords(since))
|
|
return Ledgered{rows, sum, agents, providers}
|
|
}
|
|
|
|
// Filtered narrows one snapshot without reloading either log or repricing rows.
|
|
func (l Ledgered) Filtered(f Filter) Ledgered {
|
|
if f == (Filter{}) {
|
|
return l
|
|
}
|
|
out := Ledgered{Rows: []Row{}, Agents: l.Agents, Providers: l.Providers}
|
|
for _, r := range l.Rows {
|
|
if f.keeps(r.Record) {
|
|
out.Rows = append(out.Rows, r)
|
|
if !r.IsRejected() {
|
|
out.Sum.addRow(r)
|
|
}
|
|
}
|
|
}
|
|
return out
|
|
}
|
|
|
|
// Ledger is LedgerOf's rows, sum and agents.
|
|
//
|
|
// A row's swapped is judged by the upstream names in force now, not by the
|
|
// one its call went out under: the names are read from the settings here,
|
|
// once, so a name given or changed since a call was recorded re-judges that
|
|
// call — one recorded under the name magpie knows the model by, and read
|
|
// after a name was set for it, reads as a swap although the vendor answered
|
|
// with the very model that was asked for. A record keeps the canonical id
|
|
// and the name the vendor's own reply gave (served_model) and not the name
|
|
// the request was sent under, so this is the only name there is to judge by
|
|
// — read as the name that went out, which the effort a record keeps of
|
|
// makes exact: an Antigravity account is asked for the variant of the model
|
|
// that level picks, so a reply naming that one is the model that was asked
|
|
// for and not another, whatever the family it is a level of.
|
|
// It is how ledgerWith's loop already treats the rest of a row: a provider
|
|
// renamed since is put back to the id it has now, and the names in force now
|
|
// are what the catalog lists the models under as well.
|
|
//
|
|
// Storing the name that was sent would judge each call by what it was
|
|
// really sent under, and it is the better answer, but it is not this
|
|
// function's to make: it is a field on every record the gateway writes, and
|
|
// so a change to the file's format — a column a row written by an older
|
|
// magpie has no value for, and a decision about whether an empty one means
|
|
// "no upstream name" or "unknown" — rather than a row of a report. The rows
|
|
// here are what a reader sets beside a bill, and a name in force today is
|
|
// the one whose reply a bill's model column is read against.
|
|
//
|
|
// The names are read here, once for the lot, rather than asked for a row
|
|
// at a time, so a caller already holding them — a report over the
|
|
// provider/model it was given — reads them the same way and reaches the
|
|
// same judgement: what a row says is the same however the rows were asked
|
|
// for.
|
|
func Ledger(p Period, f Filter) (rows []Row, sum Totals, agents []string) {
|
|
l := LedgerOf(p, f)
|
|
return l.Rows, l.Sum, l.Agents
|
|
}
|
|
|
|
func ledger(since time.Time, f Filter, recs []Record) (rows []Row, sum Totals, agents []string) {
|
|
rows, sum, agents, _ = ledgerWith(since, f, recs, nil)
|
|
return rows, sum, agents
|
|
}
|
|
|
|
// UnknownProvider groups local session calls without claiming a supplier.
|
|
// Recorded provider IDs and matched creator identities stay in their own fields.
|
|
const UnknownProvider = "session-unknown"
|
|
|
|
// logRecord is a call read from a session file, as a record: the upstream is
|
|
// unknown, and what the file doesn't say is left out. Nothing
|
|
// stood between the agent and the vendor, so what was sent is what the agent
|
|
// asked for. Claude Code's file names the model it asked for (as it runs) and
|
|
// the one the API answered with, which is the served model; Codex's and
|
|
// OpenCode's name only the one they asked for (OpenCode's reply keeps the
|
|
// model it was sent to, never the one the response named) (#680).
|
|
func logRecord(c sessions.Call) Record {
|
|
r := Record{Time: c.Time, Agent: c.Agent, Provider: UnknownProvider, Model: c.Model, Served: c.Model, Requested: c.Requested,
|
|
Input: c.Input, Output: c.Output, CacheRead: c.CacheRead, CacheWrite: c.CacheWrite, CacheWrite1h: c.CacheWrite1h, Reasoning: c.Reasoning, Effort: c.Effort,
|
|
Millis: c.Millis, TTFT: c.TTFT, Session: c.Session, RequestID: c.RequestID, Error: c.ErrorText, ErrType: c.Error}
|
|
if c.Agent == "codex" || c.Agent == "opencode" {
|
|
r.Requested, r.Served = c.Model, ""
|
|
}
|
|
if r.Requested != "" {
|
|
// sent as asked, less the size of its context Claude Code names it by
|
|
r.Model = contextTail.ReplaceAllString(r.Requested, "")
|
|
}
|
|
return r
|
|
}
|
|
|
|
// gatewayMatches correlates IDs first, then native session, equal token counts
|
|
// and an end within 2s. Fallback matches must be unique in both logs: an
|
|
// ambiguous direct call stays visible. One gateway entry consumes one file call.
|
|
func gatewayMatches(recs []Record, logs []sessions.Call) map[int]bool {
|
|
gateway, local := &rowChunk{}, &rowChunk{}
|
|
for i, r := range recs {
|
|
r.Agent = AgentOf(r.Agent)
|
|
gateway.add(Row{Record: r}, "", int64(i), false)
|
|
}
|
|
for i, c := range logs {
|
|
r := logRecord(c)
|
|
r.Agent = c.Agent // the native log already names its agent
|
|
local.add(Row{Record: r}, c.Msg, int64(i), c.Error != "")
|
|
}
|
|
matched := map[int]bool{}
|
|
for ref := range matchedBlocks([]*rowChunk{gateway}, []*rowChunk{local}, nil, time.Time{}, false) {
|
|
matched[ref.Index] = true
|
|
}
|
|
return matched
|
|
}
|
|
|
|
func ledgerWith(since time.Time, f Filter, recs []Record, logs []sessions.Call) (rows []Row, sum Totals, agents, providers []string) {
|
|
return ledgerWithShared(since, f, recs, logs, nil)
|
|
}
|
|
|
|
// ledgerWithShared is ledgerWith with the calls other computers made (#542),
|
|
// priced and judged here as this computer's are.
|
|
func ledgerWithShared(since time.Time, f Filter, recs []Record, logs []sessions.Call, others []SharedCall) (rows []Row, sum Totals, agents, providers []string) {
|
|
renamed := provider.Renamed()
|
|
// the upstream names in force now, read once for the lot: a row is
|
|
// judged by the names standing today, which is what Ledger says, and
|
|
// the rows here are what a reader compares a bill against
|
|
wires := settings.Load().ModelWires
|
|
priceOf := pricer()
|
|
rows = make([]Row, 0, len(recs)+len(logs))
|
|
agents, providers = []string{}, []string{}
|
|
matched := gatewayMatches(recs, logs)
|
|
identities := newSessionResolver(logs)
|
|
add := func(r Record, pr *catalog.Price, source string) {
|
|
if a := AgentOf(r.Agent); !slices.Contains(agents, a) {
|
|
agents = append(agents, a)
|
|
}
|
|
if r.Provider != "" && !slices.Contains(providers, r.Provider) {
|
|
providers = append(providers, r.Provider)
|
|
}
|
|
if !f.keeps(r) {
|
|
return
|
|
}
|
|
if !r.IsRejected() {
|
|
sum.add(r, pr)
|
|
}
|
|
sent := r.Model
|
|
if source == "" {
|
|
sent = provider.SentNameIn(wires, r.Provider, r.Model, r.Effort)
|
|
}
|
|
row := Row{Record: r, Swapped: r.Served != "" && Swapped(sent, r.Served), Routed: GroupRouted(sent, r.Served), Source: source}
|
|
if pr != nil && r.Input+r.Output > 0 {
|
|
row.Cost, row.Priced = r.CostAt(*pr), true
|
|
}
|
|
row.Agent = AgentOf(r.Agent)
|
|
rows = append(rows, row)
|
|
}
|
|
for i := len(recs) - 1; i >= 0; i-- {
|
|
r := recs[i]
|
|
if !since.IsZero() && r.Time.Before(since) {
|
|
continue
|
|
}
|
|
if id, ok := renamed[r.Provider]; ok {
|
|
r.Provider = id
|
|
}
|
|
add(r, priceOf(r), "")
|
|
}
|
|
for i, c := range logs {
|
|
if (!since.IsZero() && c.Time.Before(since)) || matched[i] {
|
|
continue
|
|
}
|
|
// Session identity does not establish a billing provider; price the
|
|
// record through the same lookup without inferring one from the account.
|
|
r := logRecord(c)
|
|
r.SessionAccount = identities.resolve(c)
|
|
r.SessionOfficialLogin = identities.officialLogin(c, r.SessionAccount)
|
|
r.SessionProvider = c.Upstream
|
|
add(r, priceOf(r), "log")
|
|
}
|
|
for _, c := range others {
|
|
r := c.Record
|
|
if !since.IsZero() && r.Time.Before(since) {
|
|
continue
|
|
}
|
|
if id, ok := renamed[r.Provider]; ok {
|
|
r.Provider = id
|
|
}
|
|
add(r, priceOf(r), c.Source)
|
|
}
|
|
// the two logs, by when each call began
|
|
sort.SliceStable(rows, func(i, j int) bool { return rows[i].Time.After(rows[j].Time) })
|
|
slices.Sort(agents)
|
|
slices.Sort(providers)
|
|
return rows, sum, agents, providers
|
|
}
|
|
|
|
// pricer uses the same effective price as the model CLI and session totals:
|
|
// explicit provider/model or provider-wide prices (including zero), then the
|
|
// provider catalog, then the maker catalog. Settings are read once per query.
|
|
func pricer() func(Record) *catalog.Price {
|
|
prices := map[[2]string]*catalog.Price{}
|
|
s := settings.Load()
|
|
return func(r Record) *catalog.Price {
|
|
k := [2]string{r.Provider, r.Model}
|
|
if pr, ok := prices[k]; ok {
|
|
return pr
|
|
}
|
|
var pr *catalog.Price
|
|
v, ok := provider.EffectivePriceIn(s, r.Provider, r.Model)
|
|
if ok {
|
|
pr = &v
|
|
} else {
|
|
catalog.Missing() // models.dev may list it by now
|
|
}
|
|
prices[k] = pr
|
|
return pr
|
|
}
|
|
}
|
|
|
|
// NewPricer totals requests' token-bearing attempts at one snapshot of the
|
|
// effective prices used by the ledger. Reuse it for one page of routes;
|
|
// make it again on the next read so a changed tariff re-prices history.
|
|
func NewPricer() func([]Record) Totals {
|
|
priceOf, renamed := pricer(), provider.Renamed()
|
|
return func(recs []Record) Totals {
|
|
var sum Totals
|
|
for _, r := range recs {
|
|
if id, ok := renamed[r.Provider]; ok {
|
|
r.Provider = id
|
|
}
|
|
sum.add(r, priceOf(r))
|
|
}
|
|
return sum
|
|
}
|
|
}
|
|
|
|
// CSVHeader is the ledger's columns, as WriteCSV writes them.
|
|
var CSVHeader = []string{"time", "agent", "requested_model", "provider", "host", "model", "served_model", "swapped",
|
|
"effort", "input_tokens", "output_tokens", "cache_write_tokens", "cache_read_tokens", "reasoning_tokens",
|
|
"cost_usd", "duration_ms", "ttft_ms", "status", "error", "session", "kind", "provider_key_id", "provider_key_name", "provider_account", "route_id",
|
|
"request_id", "endpoint", "error_message", "error_type", "source", "rejected", "session_provider", "session_account", "session_official_login", "caller_key_id", "caller_key_name", "response_id", "upstream",
|
|
"cache_write_5m_tokens", "cache_write_1h_tokens"}
|
|
|
|
// WriteCSV writes rows as CSV, a header first (cache_write_tokens is every
|
|
// cache write, as it always was, and the last two columns split it into
|
|
// 5-minute and 1-hour writes): times in RFC 3339 with
|
|
// their offset, the cost in USD at the effective price (empty when unknown), error
|
|
// "true" for a call that failed: answered with a status of 400 or more, or
|
|
// ended by an error a session file tells.
|
|
func WriteCSV(w io.Writer, rows []Row) error {
|
|
cw := csv.NewWriter(w)
|
|
cw.Write(CSVHeader)
|
|
n := strconv.Itoa
|
|
for _, r := range rows {
|
|
cost := ""
|
|
if r.Priced {
|
|
cost = strconv.FormatFloat(r.Cost, 'f', 6, 64)
|
|
}
|
|
ttft := ""
|
|
if r.TTFT > 0 {
|
|
ttft = strconv.FormatInt(r.TTFT, 10)
|
|
}
|
|
routeID := ""
|
|
if r.RouteID != 0 {
|
|
routeID = strconv.FormatInt(r.RouteID, 10)
|
|
}
|
|
cw.Write([]string{r.Time.Format(time.RFC3339), r.Agent, r.Requested, r.Provider, r.Host, r.Model, r.Served,
|
|
strconv.FormatBool(r.Swapped), r.Effort, n(r.Input), n(r.Output), n(r.CacheWrite), n(r.CacheRead), n(r.Reasoning),
|
|
cost, strconv.FormatInt(r.Millis, 10), ttft, n(r.Status), strconv.FormatBool(r.Failed()), r.Session, r.Kind, r.ProviderKeyID, r.ProviderKeyName, r.Account(), routeID,
|
|
r.RequestID, r.Endpoint, r.Error, r.ErrType, r.Source, strconv.FormatBool(r.IsRejected()), r.SessionProvider, r.SessionAccount, strconv.FormatBool(r.SessionOfficialLogin), r.CallerKeyID, r.CallerKeyName, r.ResponseID, r.Upstream,
|
|
n(r.CacheWrite - min(r.CacheWrite1h, r.CacheWrite)), n(min(r.CacheWrite1h, r.CacheWrite))})
|
|
}
|
|
cw.Flush()
|
|
return cw.Error()
|
|
}
|
|
|
|
// timeline is a period's empty timeline as of now, so quiet stretches still
|
|
// take their place: a point per hour of today, per day of a week or a month,
|
|
// and per week (from a Monday) of a longer time, which starts at first, the
|
|
// time of the oldest call. since is when it starts.
|
|
func timeline(p Period, now, first time.Time) (since time.Time, bucket string, pts []Point) {
|
|
day := time.Date(now.Year(), now.Month(), now.Day(), 0, 0, 0, 0, now.Location())
|
|
bucket, pts = "day", []Point{}
|
|
var n int
|
|
switch p {
|
|
case Today:
|
|
since, bucket = day, "hour"
|
|
case Week:
|
|
since, n = day.AddDate(0, 0, -6), 7
|
|
case Month:
|
|
since, n = day.AddDate(0, 0, -29), 30
|
|
default:
|
|
if !first.IsZero() {
|
|
f := first.In(now.Location())
|
|
since = time.Date(f.Year(), f.Month(), f.Day(), 0, 0, 0, 0, now.Location())
|
|
} else {
|
|
since = day
|
|
}
|
|
if n = calendarDays(since, day) + 1; n > 60 {
|
|
bucket = "week"
|
|
// start on the Monday of the first week
|
|
off := (int(since.Weekday()) + 6) % 7
|
|
since = since.AddDate(0, 0, -off)
|
|
n = calendarDays(since, day)/7 + 1
|
|
}
|
|
}
|
|
switch bucket {
|
|
case "hour":
|
|
for h := 0; day.Add(time.Duration(h) * time.Hour).Before(day.AddDate(0, 0, 1)); h++ {
|
|
t := day.Add(time.Duration(h) * time.Hour)
|
|
pts = append(pts, Point{Label: t.Format("15"), Time: t})
|
|
}
|
|
case "day":
|
|
for i := 0; i < n; i++ {
|
|
t := since.AddDate(0, 0, i)
|
|
pts = append(pts, Point{Label: t.Format("Jan 2"), Time: t})
|
|
}
|
|
case "week":
|
|
for i := 0; i < n; i++ {
|
|
t := since.AddDate(0, 0, 7*i)
|
|
pts = append(pts, Point{Label: t.Format("Jan 2"), Time: t})
|
|
}
|
|
}
|
|
return since, bucket, pts
|
|
}
|
|
|
|
func calendarDays(from, to time.Time) int {
|
|
date := func(t time.Time) time.Time { return time.Date(t.Year(), t.Month(), t.Day(), 0, 0, 0, 0, time.UTC) }
|
|
return int(date(to).Sub(date(from)).Hours() / 24)
|
|
}
|
|
|
|
func bucketIndex(bucket string, since, t time.Time) int {
|
|
switch bucket {
|
|
case "hour":
|
|
return int(t.Sub(since).Hours())
|
|
case "week":
|
|
return calendarDays(since, t) / 7
|
|
default:
|
|
return calendarDays(since, t)
|
|
}
|
|
}
|
|
|
|
// addRow adds a ledger row, at the cost it already has.
|
|
func (t *Totals) addRow(r Row) {
|
|
if r.TTFT > 0 && !r.Failed() {
|
|
t.Timed++
|
|
t.TTFT += r.TTFT
|
|
if n, w := r.Decode(); w > 0 {
|
|
t.DecodeMs += w
|
|
t.DecodeOut += n
|
|
}
|
|
}
|
|
t.Calls++
|
|
if r.Failed() {
|
|
t.Errors++
|
|
}
|
|
t.Input += r.Input
|
|
t.Output += r.Output
|
|
t.CacheRead += r.CacheRead
|
|
t.CacheWrite += r.CacheWrite
|
|
t.CacheWrite1h += r.CacheWrite1h
|
|
t.Reasoning += r.Reasoning
|
|
switch {
|
|
case r.Priced:
|
|
t.Cost += r.Cost
|
|
case r.Input+r.Output > 0:
|
|
t.Unpriced++
|
|
}
|
|
}
|
|
|
|
// Dimensions are what calls are told apart by: the provider they went to,
|
|
// the agent that made them, the model, and the model at the provider it
|
|
// went to ("modelAt"), so one model's speed at each provider can be compared
|
|
// (inaction on Discord).
|
|
var Dimensions = []string{"provider", "agent", "model", "modelAt"}
|
|
|
|
// ModelAtKey is a call's "modelAt": its provider's id and its model, as
|
|
// "provider/model" (a provider's id has no "/").
|
|
func ModelAtKey(provider, model string) string { return provider + "/" + model }
|
|
|
|
// key is the row's part of a dimension: its provider's id, its agent, its model.
|
|
func (r Row) key(by string) string {
|
|
switch by {
|
|
case "provider":
|
|
return r.Provider
|
|
case "agent":
|
|
return r.Agent
|
|
case "modelAt":
|
|
return ModelAtKey(r.Provider, r.Model)
|
|
case "computer":
|
|
if r.Computer == "" {
|
|
return ThisComputer
|
|
}
|
|
return r.Computer
|
|
}
|
|
return r.Model
|
|
}
|
|
|
|
// keyer is Row.key for many rows, made once for each provider and model:
|
|
// a "modelAt" is a string built of two, which a page of thousands of rows
|
|
// would otherwise build again for each.
|
|
type keyer map[[2]string]string
|
|
|
|
func (m keyer) key(r Row, by string) string {
|
|
if by != "modelAt" {
|
|
return r.key(by)
|
|
}
|
|
k, ok := m[[2]string{r.Provider, r.Model}]
|
|
if !ok {
|
|
k = r.key(by)
|
|
m[[2]string{r.Provider, r.Model}] = k
|
|
}
|
|
return k
|
|
}
|
|
|
|
// AllTokens is what went in and out and through the cache.
|
|
func (t Totals) AllTokens() int { return t.Input + t.Output + t.CacheRead + t.CacheWrite }
|
|
|
|
// Share is one provider's, agent's or model's part of some rows.
|
|
type Share struct {
|
|
ID string `json:"id"`
|
|
Totals
|
|
}
|
|
|
|
// Breakdown sums rows by a dimension, the one with the most tokens first (then
|
|
// by calls, then by name).
|
|
func Breakdown(rows []Row, by string) []Share {
|
|
at := map[string]*Share{}
|
|
var out []*Share
|
|
keys := keyer{}
|
|
for _, r := range rows {
|
|
if r.IsRejected() {
|
|
continue
|
|
}
|
|
k := keys.key(r, by)
|
|
s := at[k]
|
|
if s == nil {
|
|
s = &Share{ID: k}
|
|
at[k], out = s, append(out, s)
|
|
}
|
|
s.addRow(r)
|
|
}
|
|
slices.SortFunc(out, func(a, b *Share) int {
|
|
switch {
|
|
case a.AllTokens() != b.AllTokens():
|
|
return b.AllTokens() - a.AllTokens()
|
|
case a.Calls != b.Calls:
|
|
return b.Calls - a.Calls
|
|
}
|
|
return strings.Compare(a.ID, b.ID)
|
|
})
|
|
res := make([]Share, len(out))
|
|
for i, s := range out {
|
|
res[i] = *s
|
|
}
|
|
return res
|
|
}
|
|
|
|
// Part is what one provider, agent or model had of a point of the timeline.
|
|
type Part struct {
|
|
Calls int `json:"calls"`
|
|
Tokens int `json:"tokens"`
|
|
Cost float64 `json:"cost"`
|
|
// how fast its replies came, as Totals has it: a chart of speed says
|
|
// each one's at each point (#860)
|
|
Timed int `json:"timed,omitempty"`
|
|
TTFT int64 `json:"ttft_ms,omitempty"`
|
|
DecodeMs int64 `json:"decode_ms,omitempty"`
|
|
DecodeOut int `json:"decode_out,omitempty"`
|
|
}
|
|
|
|
// add counts a row in the part.
|
|
func (p *Part) add(r Row) {
|
|
p.Calls++
|
|
p.Tokens += r.Input + r.Output + r.CacheRead + r.CacheWrite
|
|
if r.Priced {
|
|
p.Cost += r.Cost
|
|
}
|
|
if r.TTFT > 0 && !r.Failed() {
|
|
p.Timed++
|
|
p.TTFT += r.TTFT
|
|
if n, w := r.Decode(); w > 0 {
|
|
p.DecodeMs += w
|
|
p.DecodeOut += n
|
|
}
|
|
}
|
|
}
|
|
|
|
// SeriesPoint is a point of the timeline with its calls told apart, by each
|
|
// dimension, for a chart to stack them: the models of one point, say.
|
|
type SeriesPoint struct {
|
|
Point
|
|
By map[string]map[string]Part `json:"by"`
|
|
}
|
|
|
|
// seriesKeep is how many providers, agents or models a point tells apart,
|
|
// those with the most tokens over the period; the rest are what is left of
|
|
// the point's own sums.
|
|
const seriesKeep = 24
|
|
|
|
// LedgerSeries is the rows of a period, the ledger's or a filter's, summed by
|
|
// hour, day or week, for the chart over them. A row is of the point its
|
|
// time falls in; the rows are in any order.
|
|
func LedgerSeries(p Period, rows []Row) (bucket string, pts []SeriesPoint) {
|
|
return ledgerSeriesAt(p, rows, Clock())
|
|
}
|
|
|
|
// ledgerSeriesAt is LedgerSeries with the period read at now, the moment the
|
|
// rows were read at, so that the chart is of the rows' day.
|
|
func ledgerSeriesAt(p Period, rows []Row, now time.Time) (bucket string, pts []SeriesPoint) {
|
|
var first time.Time
|
|
for _, r := range rows {
|
|
if r.IsRejected() {
|
|
continue
|
|
}
|
|
if first.IsZero() || r.Time.Before(first) {
|
|
first = r.Time
|
|
}
|
|
}
|
|
since, bucket, base := timeline(p, now, first)
|
|
pts = make([]SeriesPoint, len(base))
|
|
for i := range base {
|
|
pts[i] = SeriesPoint{Point: base[i], By: map[string]map[string]Part{}}
|
|
for _, d := range Dimensions {
|
|
pts[i].By[d] = map[string]Part{}
|
|
}
|
|
}
|
|
kept := map[string]map[string]bool{}
|
|
keys := keyer{}
|
|
for _, d := range Dimensions {
|
|
kept[d] = map[string]bool{}
|
|
for i, s := range Breakdown(rows, d) {
|
|
if i < seriesKeep {
|
|
kept[d][s.ID] = true
|
|
}
|
|
}
|
|
}
|
|
for _, r := range rows {
|
|
if r.IsRejected() {
|
|
continue
|
|
}
|
|
t := r.Time.In(now.Location())
|
|
if t.Before(since) {
|
|
continue
|
|
}
|
|
i := bucketIndex(bucket, since, t)
|
|
if i < 0 || i >= len(pts) {
|
|
continue
|
|
}
|
|
pts[i].addRow(r)
|
|
for _, d := range Dimensions {
|
|
if k := keys.key(r, d); kept[d][k] {
|
|
part := pts[i].By[d][k]
|
|
part.add(r)
|
|
pts[i].By[d][k] = part
|
|
}
|
|
}
|
|
}
|
|
return bucket, pts
|
|
}
|
|
|
|
// Visit calls fn with each record from since on, as the ledger's index
|
|
// reads usage.jsonl: only its blocks that reach since are decoded.
|
|
func Visit(since time.Time, fn func(Record)) { readLogSnapshot().visit(since, fn) }
|
|
|
|
// NewCoster prices one record at a time at the effective prices the
|
|
// ledger uses, read once: its cost in USD, and false for a call with
|
|
// tokens but no known price.
|
|
func NewCoster() func(Record) (float64, bool) {
|
|
priceOf, renamed := pricer(), provider.Renamed()
|
|
return func(r Record) (float64, bool) {
|
|
if id, ok := renamed[r.Provider]; ok {
|
|
r.Provider = id
|
|
}
|
|
var t Totals
|
|
t.add(r, priceOf(r))
|
|
return t.Cost, t.Unpriced == 0
|
|
}
|
|
}
|