main
42
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 yetone
|
3e5bc3d8fe |
gateway, usage: conversation text is kept only under a session the client named, and a client's "request-…" session counts like any other (#1355)
What changed: with recording on, a request that names no session used to get a made-up "request-…" id and its text saved under it. Nothing listed that id and GatewaySessionByID turned it away, so the text could never be opened. magpie now makes up no id: such a request isn't recorded, and the X-Magpie-Session reply header only echoes the client's own session. With no made-up ids left, the "request-" prefix checks in appendUsage, OTel, Usage's sessions, Routing's vias and the gateway Sessions projection only dropped sessions clients named themselves (appendUsage wiped them from the ledger). They are gone. The tests that held the old rule now say the new one, and gateway-sessions.md says it. Run: TestGatewayConversationNeedsTheClientsSession and TestGatewayConversationClientRequestPrefixedSession fail on the PR's code (a made-up id is returned; the ledger keeps 0 of 2 calls) and pass here; putting appendUsage's prefix check back turns the second red again. gofmt -l clean; go vet; GOOS=linux and GOOS=windows go vet -tags nogui on gateway, gui, sessions, settings, usage; go test -race -timeout 900s on those five: ok (gateway's TestCORSKeyThroughTheServer rerun after its fix). GUI: gateway-conversations, gateway-mode and all sessions-* tests, 216 cases in Chromium and WebKit: pass. |
||
|
木子不是木子狸
|
c9b8263378 |
sessions, gateway: Sessions lists gateway sessions, and can keep their text on this computer when turned on (#1355, mu-zi-lee)
What changed: the Sessions page lists sessions seen only through the gateway (from the usage ledger, read-only, a native session of the same id wins), and shows in gateway mode. A Sessions switch, off by default and confirmed before it turns on, records each gateway exchange's text under the config dir (scrubbed, at most 7 days and 256 MiB, cleaned hourly). Settings sync and restore can't turn it on; POST /api/sessions/recording turns it on or off and can clear what was kept. Why: users of magpie as a gateway (gateway mode, LAN clients) had no way to see their conversations; the owner chose this design on the PR. Squashed from PR head 6a343ba1 onto origin/main. Conflicts: gui-shell.md (kept main's placeMenu text, took the PR's Sessions in gateway mode) and settings_keep_test.go (main's fields plus GatewayConversations). Run: go build ./..., go vet on gateway, gui, sessions, settings, usage; go test -race -timeout 900s on those five packages: all ok. |
||
|
yetone
|
ed31293c0e |
usage, gui: a reply its vendor let go in a burst over a couple of hundred milliseconds tells no speed, not 2,237 tok/s (John on Discord)
John's Kimi Code rows after v0.1.1119 (OpenCode, group/k3-glm, api.kimi.ai,
Chat, k3-256k): 550 tokens, 22 of them reasoning, in 16 s with the first
content at 5.2 s read 2,237 tok/s, and 395 tokens in 19 s 2,012. 528 answer
tokens at 2,237 tok/s is 236 ms: the burst the vendor let go at the end.
|
||
|
yetone
|
de5455b8fe |
gateway, usage, gui: a reply whose vendor sent its first words and held the rest to send in one burst tells no speed, not 1,367 tok/s (John on Discord)
John's request (OpenCode, a group served by Kimi Code at api.kimi.ai, Chat) showed 1,367 token/s: its tokens counted over the time from its first token to its end, though nothing came in between and the rest came at once. The 100 ms / 10,000 tok/s bounds catch a burst only when the first content comes with it. firstToken now reads on past the first text and marks when each content event's bytes came (one mark a millisecond, up to 65,536 marks and the 8 MB it reads), and flowMs is how long the content took to come from where the speed is counted: the span from a tenth of its bytes to nine tenths, scaled to the whole. A steady stream gets about its whole window; one let go in a burst about 1 ms. It is kept as Call/Try/Route .flow and usage.Record.flow_ms (and the Requests page's packed rows), and usage.DecodeOf, routing.js's decodeOf and app.js's ledDecode count no longer a window than it. A record without it reads as before. Verified: TestBurstTellsNoSpeed, a fake Chat vendor that sends a word, waits 600 ms, then 199 words and the end in one write (1,000 tokens), for a Chat and a Responses agent: no speed; before, 1636 and 1655 tok/s. Its steady case (a word every 60 ms) keeps 200 tokens over most of its window. TestCodexBackendBurstTellsNoSpeed is the same through Codex's own ChatGPT backend (before: 1,000 tokens in 601 ms). TestFirstTokenKinds now expects the stream read past its first text. Go tests ran on Linux (golang:1.26 in Docker; this Mac's syspolicyd held new test binaries at launch). GUI: routing-burst-speed (a route with John's 5.1 s first token, 6.7 s and a 2 ms flow: was "1367 tok/s", now none) and usage-speed (a row with flow_ms 2 shows "—") fail without the JS change and pass with it, with reasoning-speed, routing-request-metrics and usage-ledger-detail, in Chromium and WebKit (en/zh, ja/de where the tests have them); no strings changed. Not reproduced with Kimi Code itself: whether it holds the stream so is inferred from the numbers. |
||
|
forever
|
e961836fb0 |
usage, gateway, gui, provider, cli: the tests pass when a run crosses midnight, and a usage answer reads the clock once (#1046)
* 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 since |
||
|
yetone
|
e6dd5d20bb | usage, gateway, gui: a reply that reasoned is timed by its answer, from its first text, not by all its output from its first token (tony on Discord #general: Usage › Requests read "gpt-6.1-sol 163 token/秒 · 8,036 个请求 · 首字 14 秒" and asked whether subagents were added up) — speed was every output token over the time after the first content (text, reasoning or a tool call). Output counts the reasoning, and a model whose reasoning is hidden (OpenAI's encrypted reasoning, a summary sent when it is done, Claude's omitted thinking) writes it before the stream shows anything, inside the TTFT; so a 2,000-token think and a 200-token answer over the 1.5 s after the first token read 2,200 in 1.5 s, 1,467 tok/s. Concurrency was not the cause: the aggregate is Σ tokens over Σ per-request windows, so subagents running at once never add up. In the owner's own usage.jsonl codex/gpt-6-luna turns read up to 600 tok/s (out 496, reasoning 224, 11,055 ms, ttft 10,228) and its aggregate 133; it is 80 now. usage.DecodeOf is the one rule: a reply with reasoning counts out − reasoning over ms − firstText, one that reasoned and wrote only tool calls tells no speed, one without reasoning is timed from its TTFT as before; DecodeWindow's burst cut (#731) still applies. Record.Decode feeds summarize, the ledger's Totals and its timeline Parts; a route keeps its reply's reasoning (Route.Reasoning, from gateway.go and codex_backend.go), and routing.js's decodeOf/speedOf times its rows, the story and a session's average by it (an older route takes its served usage's reasoning); app.js's ledDecode does the Usage page's rows, whose tooltip says the reasoning left out, and the Output speed help says the rule, in en, zh, ja and de. History is read the same way, as it keeps the reasoning and the first text. Routing never ranks by speed. TestReasoningReplyTimedByItsAnswer (the 2200/2000 turn, a summary 10 ms before the text, a concurrent subagent, tool calls only, reasoning over output, no reasoning, not streamed: 1,200 tokens in 11 s through summarize, addRow, LedgerSeries and Decode) fails without the change and passes -race -count=10; TestUsageKeepsTimeToFirstToken now has its paced replies report reasoning and checks the route keeps it. reasoning-speed.test.cjs (Routing rows 133, 100, none and 100, the story never 1,467, the session 105; the Usage rows, tooltip and KPI the same; no sideways scroll) passes on Chromium and WebKit in en, zh, ja and de, and fails against the old assets (1467 tok/s); routing-request-metrics, routing-burst-speed, usage-speed, usage-ledger-detail, i18n-keys, gui-ja, gui-de, ledger-hscroll and click-scroll pass on both. go test -race -tags nogui ./internal/... under a temp HOME passes but internal/proc's TestUserPath ("the login shell's PATH never came"), which failed under the full run's load, passes 3/3 alone and is not touched here; go vet, gofmt -l, linux and windows (nogui) builds pass. Not tried with tony's data. docs/reference.md says how output speed is counted. | ||
|
yetone
|
c5b57b9077 |
gateway, usage, gui: a relay's reply of tool calls ended "end_turn" or "tool_calls" goes on to the calls, a tool_use whose start carries its input keeps it, an Anthropic stream that just stops is an error, and every request says its protocol and the upstream's stop reason (蓝猫 on Discord)
蓝猫's custom Anthropic-protocol provider in front of Grok ended the agent's
turn a few words in with no error, where Alma on the same endpoint ran on.
Replayed from a fake upstream, three ways an Anthropic-shaped relay's
stream was read wrong when magpie translated it for an agent of another
protocol:
- a reply of tool calls whose stop_reason said end_turn, stop or OpenAI's
tool_calls was handed on as finish_reason "stop": the agent ended its
turn instead of running the calls. stopFromAnthropic takes tool_calls,
function_call, length and content_filter; collector.finish makes a
"stop" beside tool calls "tool".
- a tool_use block whose content_block_start carries its whole input,
with no input_json_delta after, lost the input (the call went with {}).
anthropicDecoder emits it, and skips deltas for that block after.
- a stream that ended cleanly with no stop_reason and no message_stop was
finished as a whole reply. streamTranslated now takes it as cut: asked
to go on where it can, else ended with "the reply ended before it was
complete", as the passthrough already did.
Each request now keeps the upstream's own stop reason (Usage.Stop /
usage.Record.stop: stop_reason, finish_reason, a Responses status), from
the passthrough's sniffer and the translated stream, shown as "Upstream
stop reason" in a request's details on Usage › Requests. Each row there
is tagged with the protocol it was sent upstream in, "Chat → Anthropic"
when translated, told from its endpoint, so older rows have it too; the
details say Protocol. en/zh/ja/de, no left border, no select, a click
moves nothing.
relay_stop_test.go's four tests fail without the change (finish_reason
"stop" for tool calls under end_turn/tool_calls/stop, arguments "" for a
whole-input start, a cut stream finished "stop", no stop recorded) and pass
with it; the passthrough case sends "data:" without a space and CRLF.
ledger-protocol.test.cjs passes in Chromium and WebKit, en and zh.
go vet, go build (darwin, GOOS=linux nogui, GOOS=windows) and go test
-tags nogui ./... under a temp HOME pass.
|
||
|
yetone
|
71d2da1f42 |
catalog, usage, gateway, gui: a price can have a long-context tier and a 1-hour cache write, and the price boxes take decimals (PAMI on Discord)
OpenAI bills gpt-6-astra, gpt-6.1-sol and gpt-6-luna over 272K input at 2× input and cache and 1.5× output, for the whole request. A price now has tiers: `magpie model price <m> 10,50,1,12.5 --tier 272k 20,75,2,25` (--tier can repeat). A tier applies when input + cache reads + cache writes is over its size, so 272,000 is not over and 272,001 is. The built-in prices take tiers only where models.dev lists one (cost.tiers of type "context"), and it does list one for those three. The ledger, each request and OTLP are costed at the tier the call reached. Session and day totals sum many calls, so they stay at the base price.
Anthropic bills a cache write kept for an hour at 2× input and one kept for 5 minutes at 1.25×. Its usage reports which is which in cache_creation.ephemeral_5m/1h_input_tokens. The gateway (API and Claude subscription) and Claude Code's transcripts now keep that split. A price's fifth part is the 1-hour write. When it isn't given, it is 2× input: that is Anthropic's rule, and only Anthropic reports 1-hour writes. Claude list prices carry the 2× too. cache_write_tokens is still the total, and the usage CSV adds cache_write_5m_tokens and cache_write_1h_tokens at the end. The app shows the split on a request's Cache and on the usage tooltips. Old prices and old records, which have no 1-hour part, read as before. The sessions cache (18) and the call cache (calls-v8) are re-read once.
In the GUI, the price boxes were number inputs and dropped what they didn't parse ("0,25"). They are now decimal text boxes that take both "0.25" and "0,25". A model's price row has a 1-hour box (empty means 2× input) and a quiet Long-context price row. That row shows the list's tier greyed in, or sits behind a link when the list has none. A bad size is refused by name. en/zh/ja/de.
Tests:
- New: TestPriceTiers, TestCostSplit, TestPriceJSON, TestModelPriceTiers, TestModelPriceTierCmd, TestAnthropicCacheWriteSplit and TestClaudeCacheWriteSplit. The ledger CSV test expects the new columns.
- model-price-tiers.test.cjs is new; model-price-edit and provider-price-rate are updated. All of them fail against the old assets and pass in WebKit. Chromium couldn't be launched here.
- go vet, go build (darwin, GOOS=linux nogui, GOOS=windows) and go test -tags nogui ./... under a temp HOME pass.
|
||
|
yetone
|
e5981040dc | gateway, gui: a request an aggregator passed on says which provider answered it behind it, "Upstream: DeepInfra" (leslie_luo on Discord: 像 CPA 那样指出实际供应商) — through OpenRouter a request was only "OpenRouter · deepseek/deepseek-chat", with no word of the provider (DeepInfra, StreamLake, Novita…) OpenRouter had sent it on to. OpenRouter names it in its replies, as tried with the owner's real key: Chat's body and every chunk of its stream have a top-level "provider", Messages' body has one and its stream's message_start a message.provider; its Responses replies and every reply's headers name none. The gateway now reads it (upstreamOf) from a body relayed as it came and from each event of one it translated, Chat, Messages or Responses, streamed or not, and keeps it on the request's try and route (upstream) and in the usage ledger (Record.Upstream; the CSV export's last column, searched as the rest). The Routing page's Requests list says Upstream: DeepInfra beside where it went, giving way after the provider's name when short of room, with its story saying the aggregator passed it on; a request's details on the Usage page have Upstream provider. A reply naming none says nothing. zh, ja, de strings. ClinePass and Cline weren't tried (no account); Vercel's gateway documents no such field in its replies, and a vendor whose reply has a top-level "provider" string is read the same way. In a sandbox magpie with the owner's real OpenRouter key: Chat, Messages and Responses (translated to Chat), streamed and not, all six said StreamLake in the trace, the ledger and on the Routing page. TestUpstreamRecorded (6 paths × streamed or not: the route, its try, Recent and the ledger) fails on the old code, TestUpstreamOf; routing-upstream.test.cjs (Chromium and WebKit, en and zh: the tag inside its row, the story, the Usage details, a click moves nothing, no left-border accent) fails on the old assets. ledger-hscroll, request-archive-usage, usage-ledger and usage-ledger-detail pass on WebKit; routing-served fails the same on origin/main (its swap wording). go vet, builds (darwin, GOOS=linux nogui, GOOS=windows) and go test -tags nogui ./... under a temp HOME pass but for TestTranslatedStreamKeepsClientAlive, which passes alone 5 times here and on origin/main. | ||
|
yetone
|
258eae592d |
agent: Cursor Private Inference, which magpie finds by its product.json and starts on magpie with a command its row copies, and whose /models gives each model's api_types and capabilities (#299, mamba on Discord) — the build (Cursor 3.23.x, the same app name, bundle id and ~/.cursor as Cursor) runs its agent locally and asks the endpoint in CURSOR_LOCAL_AGENT_BASE_URL / CURSOR_LOCAL_AGENT_API_KEY when its Open configuration has none; mamba confirmed it works with any account pointed at magpie. magpie writes nothing of Cursor's (its settings share Cursor's state.vscdb): the Agents page lists it when an app's product.json says "Cursor Private Inference" (/Applications, ~/Applications; %LOCALAPPDATA%\Programs on Windows; /opt and the like on Linux), and its row's one control, Copy launch command (复制启动命令), copies CURSOR_LOCAL_AGENT_BASE_URL=<gateway>/v1 CURSOR_LOCAL_AGENT_API_KEY=magpie-cursor-local '<app>' (PowerShell on Windows); in the tray panel the row copies it. Its notice says to quit it first (a second start hands over to the running one) and that a base URL in Open configuration comes first. /v1/models asked with its key gives each model api_types (the APIs its provider serves it on, all three for a group or a translated one; it asks Anthropic Messages only when no OpenAI one is listed) and capabilities (context_length, max_output_tokens, supports_vision); any other client's list is unchanged. usage.AgentOf matches a name before a UA prefix, so cursor-local isn't counted as Cursor. TestCursorLocal, TestCursorLocalModels and cursor-local-launch.test.cjs (WebKit, en and zh) fail on the old code; agy-launch and agent-* GUI tests pass on WebKit. Not tried with the real app (not installed here). go vet, builds (darwin, GOOS=linux nogui, GOOS=windows) and go test -tags nogui -count=1 ./... under a temp HOME pass.
|
||
|
yetone
|
6f64956f27 | routing: a group can let a member go that hasn't begun answering after a set time and ask the next, and a request's detail splits its first token into magpie's time and the vendor's (Chen on X: answers through magpie felt slow, with no way to tell whether magpie or the vendor was the wait) — a group's editor has a Slow to start row (Wait, 30 s, 1 min, 2 min; Wait, the default, keeps today's behaviour). With a time set, a streamed request to a member that has sent no text, reasoning or tool call by then is cancelled before any of its bytes reach the agent (the held start is dropped; keepalives go on meanwhile) and the next member is asked; the try is marked slow ("slow to start", narrated in the route), and the member doesn't rest, since nothing is wrong with it. The last member left is always waited for. The card says "Next after 1 min without a first token". Each request now records when it went to the vendor (httptrace WroteRequest, sent_ms), and its detail shows In magpie and Vendor's first token beside First token; after a failover In magpie includes the time spent on the members let go. With the owner's real DeepSeek key in a sandbox, a group [a local member that sends its role chunk then stalls 60 s, deepseek-flash] with 3 s: the answer came from DeepSeek in 4.4 s, none of the stalled member's stream reached the client, its try read slow / "no first token in 3s" with no rest, and the ledger had ttft 3622, sent 3003. TestGroupFirstTokenFailsOver (failover, the last one waited for, one in time kept; passes -race) and group-first-token.test.cjs and usage-ledger-detail.test.cjs (WebKit, en and zh) fail on the old code. group-from-model-add's narrow-window case fails the same on origin/main; Chromium doesn't launch in this sandbox. go vet, builds (darwin, GOOS=linux nogui, GOOS=windows) and go test -tags nogui -count=1 ./... under a temp HOME pass (TestProvidersAnswerWhileListsComeIn flaked once, passes alone). | ||
|
yetone
|
91fbf15fec | usage: a reply that came in one burst at its end tells no tok/s, and is left out of the summed speed (#731, Arcadia822: a Gemini turn through Antigravity that was one write tool call, out 8264, ms 24360, ttft_ms 24359, read 8,264,000 tok/s and lifted the Usage page's average) — a reply's speed is out ÷ (ms − ttft_ms) since #196, and the sums are Σout ÷ Σ(ms − ttft_ms) (Totals.DecodeOut/DecodeMs). codeassist hands a native functionCall over whole, so a turn whose only content is one big tool call has its first content event a millisecond or two before the end: the window covers delivery, not writing, and its tokens over next to no time read millions a second and pull the summed speed up (the test's three calls: 100 tok/s each in truth, 616 with the burst counted). A decode window now counts only when it timed the writing: usage.DecodeWindow gives 0 when it is under MinDecodeMs (100 ms) or the tokens over it would be past MaxDecodeSpeed (10,000 tok/s), both far from any real stream (the fastest vendors write a few thousand a second); Totals.add (records) and Totals.addRow (ledger rows, which the Usage page sums) both go through it. Such a reply still counts as timed and its TTFT in the mean; only its speed is left out, so a model with only bursts shows no tok/s (the Usage page and the CLI already skip a speed with no decode window). The Routing page's story, which works out a try's speed itself (routing.js speedOf), applies the same bounds, so the burst says "first token in 24 s" and no tok/s. app.js's figure is decode_out ÷ decode_ms from the Go sums and needed no change. Tests: TestBurstTellsNoSpeed (the report's record with two 100 tok/s calls: 100 tok/s summed through summarize and addRow, TTFT mean keeps the burst; DecodeWindow's edges: 1 ms, 0 ms, 3 tokens in 50 ms, 8264 in 500 ms, exactly 10,000 tok/s over 100 ms, nothing written, not streamed) fails on the old rule with 616 tok/s; TestSummarizeTimesFirstTokens unchanged. routing-burst-speed.test.cjs (webkit, en and zh: the report's burst and a 500 ms one tell no speed, 100 and 50 tok/s replies keep theirs, picking a request doesn't move the page) fails on the old routing.js with "8264000 tok/s". routing-sessions, routing-served, routing-effort-change, usage-accounts, panel-usage and click-scroll GUI tests pass in webkit (routing-served failed once in a parallel run and passes on its own twice; its fixture has no TTFT). go vet, builds (darwin, GOOS=linux, GOOS=windows) and go test -tags nogui -count=1 ./... under a temp HOME pass. Not tried with the reporter's ledger or a live Gemini stream; a short reply under 100 ms (a title, a few tokens) no longer counts toward the speed either, which moves a summed figure by next to nothing. | ||
|
Fanbuz
|
c9d0d15b94 | fix: 记录网关实际返回的响应 ID (#693) | ||
|
mofelee
|
38b4a9d984 | feat: export gateway and agent conversation waterfalls to Langfuse (#581) | ||
|
Snowyy
|
3d8c6f24c5 |
usage: capture Windows change time for cached logs (#594)
* usage: capture Windows change time for cached logs * ci: show native Windows usage test outcomes |
||
|
yetone
|
5332c0c638 | usage: each subscription account's tokens and cost, by the account that answered (#557: 希望用量账本能按订阅账号统计，每个 Codex / Claude 账号各用了多少 token、多少钱) — a call's record named the upstream key it went out on (ProviderKeyID/Name, #500) but never the subscription account, so with two Codex accounts signed in, or a Claude account that took over after a failover, the ledger could say what Codex cost and not what each account did. A record now carries providerAccount, the account that answered as the Routing trace names it (Account.User: its email or login, never a token), set by the gateway at the try that went out (the candidate loop's last try, so a failover's answer is the account that took over and the refused try stays the first account's; an X-Magpie-Account pin is the pinned one), and on the decide, draw and video paths too. Record.Account() gives it, or for a record written before the field the account its host named (Where() has long written "chatgpt.com as dee@example.com" for an account), and otherwise "" — shown as "account not recorded", never inferred from today's sign-in. The summary groups calls by provider and account (Summary.Accounts, the same email on Codex and on Claude being two accounts), priced as every other group; the ledger's Filter has Account, the search finds a call by its account, the CSV has a provider_account column beside provider_key_name (the provider's identity columns together, the caller's still last), and the Requests page's packed rows keep it and offer the period's accounts. magpie usage prints an accounts table after the provider keys, and magpie usage --csv --account <name> keeps one account's calls. The app's Usage page lists Accounts on the Overview (tokens and cost per account, the provider under its name, an unrecorded one in the faint colour, no stripe down a row's side) and has an Account filter on Requests, each account noting the providers it answered for, which asks for and exports that account's calls without moving the page. OTLP export is an allowlist and does not carry the account. TestUsageNamesPinnedAccount (both pinned accounts on magpie's endpoint and on Codex's own, the trace's Who and the record agreeing, no token in usage.jsonl) and TestUsageNamesAccountThatTookOver (Ordered routing, the first account refusing: the answer recorded as the spare, the refusal as the first) fail without the gateway change; TestSummaryByAccount, TestLedgerByAccount and TestRequestPageByAccount cover the grouping, the host fallback, "not recorded", keyed providers kept out, the filter, the search, the CSV column and the packed rows; TestLedger and TestLedgerWithSessionLogCalls take the new column. usage-accounts.test.cjs (WebKit and Chromium, en and zh: the Overview's accounts and costs, the Account picker's notes, its request and export, All accounts clearing it, scrollTop unchanged) fails without the asset change; api-key-usage, click-scroll, panel-usage, request-archive-usage, tray-usages, claude-usage-asked and every usage-* test pass in WebKit. go vet ./internal/..., go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui -count=1 ./... under a temp HOME pass (TestFXInState failed once on its TempDir cleanup, passes alone). | ||
|
Snowyy
|
9657d3e9d8 | usage: reuse incremental log blocks and index CSV matches (#550) | ||
|
yetone
|
da834411b5 |
usage: with WebDAV or S3 sync, each computer shares its usage and sees the others', the total and each computer's part (#542) — sync carried keys, agents and the library, and each computer's Usage page counted only the calls made on it. Sync now has a Usage tick (off unless picked, usage=yes in magpie webdav/magpie s3): a computer with it on puts its own calls up as one file a day, magpie/usage/<id>-<day>.magpie-usage beside the bundle (under the prefix's usage/ on S3), each a gzipped list of times, agents, providers, models, tokens, costs and statuses, sealed with the sync passphrase (backup.SealData, the key cached per passphrase so a sync derives it once); no request body, session, archive name or key goes, a call another computer passed on over the LAN (Via) isn't put up again, and an error is cut to 300 characters. The id is a random one kept in usage-computer.json, which no backup carries, with the host name beside it. A computer only ever writes and deletes its own names, so none overwrites another's; the files are not in the bundle and its hash, so sharing usage never makes a sync or a conflict of the bundle; the first sync puts up the last 90 days, after that only yesterday and today, at most every 15 minutes (a Save or Sync now at once), and a day past 90 is deleted by the computer it is of. The others' files, listed (PROPFIND Depth 1; ListObjectsV2) and fetched only when changed, are kept in usage-others and read with the ledger, as Record.Computer; a failure is said in the sync row ("Couldn't share usage") and never fails the sync. The Requests page and the panel's Usage tab get a Computer pick (this computer, other computers when more than one, each by name) sending computer=this|others|<id>; a row from another computer says "· on <name>" beside its agent, and its details name the computer and say what was said stays there, nothing asked of this computer's session files for it. With no other computer's usage there is no pick and nothing new on either page, and an older magpie never lists or reads usage/. TestUsageSharedBetweenComputers (computers a and b over a fake WebDAV under httptest: each sees 4 calls, the totals and its own and the other's part, nothing counted twice over repeated syncs, the bundle not put again for usage, a new call reaching the other, a day past the window deleted), TestUsageSharedThroughS3 (the same through a fake S3, signed list and delete, a prefix with a space and a plus) and TestUsageOffAsksNothing are new and don't build without the change; usage-computers.test.cjs (WebKit, en and zh: no pick without other computers, the pick and computer=this, another computer's row and details with no /content asked, the panel's pick, the sync form's tick posting usage: true, no click moving the page) fails without it on all but the no-other-computers case. s3-sync, sync-other-kind, panel-usage, request-archive-usage, click-scroll and usage-ledger-chart pass in WebKit. go vet ./internal/..., go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui -count=1 ./... under a temp HOME pass (TestFXInState failed once on its TempDir cleanup, passes alone). Turning the Usage tick off, or sync off, lets the other computers' usage kept here go (DropAllShared), so the Usage page counts this computer's alone again: TestUsageSharedBetweenComputers checks both, and fails without it.
|
||
|
yetone
|
2f02a767b7 | otel: request and response bodies can go with a call's span, as Langfuse's input and output, behind a switch that is off by default (#538: Langfuse 似乎无法看到请求体，如果技术上好实现的话，希望可以加一个开关) — the OTLP export sent only an allowlist of metadata (model, tokens, status, timing), never a body, so a Langfuse trace had no Input or Output. Settings → Observability has a new row, "Include request and response bodies" (otel.bodies, MAGPIE_OTEL_BODIES overriding it as the other MAGPIE_OTEL_* do, and counted in the "environment variables override" note). When it and the export are on, the gateway hands the call's captured request and reply (the Recent-calls capture, first 256 KiB each, "… (cut here by magpie)" added when cut) to its usage record as BodyIn/BodyOut, json:"-" so they never reach usage.jsonl, scrubbed with redact.ScrubJSON as the request archive's are (on top of Mask secrets' placeholders); the span carries them as langfuse.observation.input and langfuse.observation.output. A streamed reply's output is its text put together from the events (Chat's choices[].delta.content, Responses' response.output_text.delta, Anthropic's content_block_delta), a reply that isn't a stream or has no text (tool calls only) going as it came. This is filled for the final record, a locally turned-away request, and an attempt refused before another account was tried (its refusal as output); draw/video/decide and Codex's own-login passthrough still send metadata only. Queued records keep the config they were queued under, so turning bodies off drops any not yet sent, and spans with bodies go four to a request so a batch stays well inside a collector's size limit. The OTLP export row's text now says credentials stay local and prompts and replies too unless bodies are included. Nothing was sent to a real collector or Langfuse. TestOTelExportsBodiesWhenOn (off: no input/output and no prompt in the export; on: the request as input, the reply as output, a streamed reply's text as output, a key in the request scrubbed) fails without the gateway change, and without the scrub; TestBodiesStayOutOfTheLog, TestOTelReplyText, TestOTelSettingsAndOverrides (MAGPIE_OTEL_BODIES) and otel.test.cjs (the row off at first, en and zh, a click saves bodies:true without scrolling, kept through another preference's save; WebKit) pass. go vet ./internal/..., go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui -count=1 ./... under a temp HOME pass. | ||
|
Aliceandraper
|
0260716c9d |
feat(usage): 可选的 OTLP 元数据导出（Trace/Metrics，支持 Langfuse） (#412)
* usage: add opt-in OTLP HTTP metadata export Export gateway traces and optional duration/token histograms asynchronously with a bounded queue, retries, proxy support and a bounded shutdown. Add bilingual Settings controls and MAGPIE_OTEL_* overrides. Keep prompts, replies, sessions and provider credentials local; use the same OTLP path for Langfuse. Validated: full Go tests (nogui), usage race tests, focused go vet, and Chromium/WebKit settings tests in English and Chinese. Refs #213 * otel: protect collector credentials in backups and settings Remove all OTLP headers from keyless backups and restrict both new and existing settings files to 0600 before saving. Clarify SIGTERM export behavior. Addresses the two blocking review findings in #412. * otel: preserve local credentials and read-only settings on restore --------- Co-authored-by: raper <raper@raperdeMacBook-Air.local> |
||
|
yetone
|
3c04877cfc | archive: a request the archive kept is opened and downloaded from the Usage page, with its bodies whole (jorben, #447: 请求存档 reachable from usage history, full bodies, download) — the archive's name was only on the Gateway page's recent calls, gone once a call left the list or the gateway restarted, and the archive kept the first 256 KB of each body, the recent list's cut. The usage ledger's row now names the call's archive (archive in usage.jsonl, kept through the Requests page's packed rows), and its details on Usage → Requests show the Request archive panel, Fetch from archive and Download; with the archive on, a request it has no copy of says "Not archived". The bodies are kept whole up to requestArchiveMaxMB in settings.json (32 MB unless set, at most 1024): the response is teed to a temp file as it is sent, the request body written to one when the call ends, so the upload queue holds file handles, not bodies, and one upload at a time reads them; a body past the limit is kept to it and marked cut, with its whole size. What goes upstream is unchanged, the archive stays off unless turned on, headers and bodies are scrubbed as before, and the temp files are removed after the upload or when the queue is full. The page is sent a body to show only when it is 256 KB or less (a longer one is said by its size), an archive over 80 MB is only said to be; Download streams the object whole, to Downloads in the app (archive/export, -2, -3… for a name taken) and as the browser's download in magpie web (archive/file). TestArchiveWholeBodies, TestArchiveLimit, TestRowKeepsArchive and TestArchivePreviewAndDownload fail without the change; TestArchiveOffUsage, TestArchiveTooLargeToPreview, TestArchiveOldPreview keep the rest. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass; request-archive-usage (new), request-archive, click-scroll, old-webkit, usage-ledger, usage-ledger-detail, usage-ledger-content, web-page, sse-body pass. | ||
|
Ns2Kracy
|
bb1aa3acbd |
feat(gateway): named gateway keys with per-client usage (#344)
* feat(gui): show and filter usage for each API key * feat(gateway): issue per-user caller keys and attribute usage * feat(gui): manage gateway users and filter caller-key usage * test: verify caller-key failover and document user management * refactor(gateway): use named caller keys without user accounts * feat(gui): manage named caller keys with existing account styles * fix: remove user breakdown from CLI and leftover gateway styling * fix(usage): drop stale user field from request response * feat(gateway): authenticate LAN calls with named caller keys * fix(gateway): preserve LAN key rotation in the named caller store * fix(gui): retain native LAN key copy and rotation controls * fix(gui): inherit the global theme for API key inputs * fix(usage): show client API keys using the existing terminology * fix(gateway): rotate named keys without changing usage identity * fix(gui): unify gateway keys and selectable connection examples Keep sharing controls in Settings and manage credentials only in Gateway. Refresh the named-key list on navigation, ignore stale reads after key actions, and generate all API examples from the selected address and enabled key. * fix(gui): keep caller key names literal in connection menus * fix(access): use Magpie as default key and drop user migration * refactor(gui): name caller key source and tests consistently * refactor(usage): split provider-key accounting out of caller-key PR * fix(gateway): preserve LAN compatibility and add headless key management * fix(gui): clarify gateway keys and confirm destructive actions * test(gateway): guard caller attribution under 120 concurrent requests * fix(gateway): keep open access, tolerate migration errors and revoke legacy keys * fix(backup): preserve named gateway keys and honor no-keys restores * fix(gui): keep local API-key semantics and disambiguate shared credentials * docs(gateway): keep review scope focused and append browser test documentation * fix(backup): retain existing default keys when old backups lack their store * fix(gateway): attribute video creation usage to the caller key * fix(access): explain default key revocation blocked by read-only settings * test(usage): preserve provider and caller identities after rebase * test(gui): reconcile caller key fixtures with merged main * docs(usage): clarify caller coverage and independent provider accounting * fix(gui): initialize fast members for model-shortcut groups Latest main introduced fast-member arrays but omitted the model shortcut's draft. The existing unlisted-models browser regression fails unchanged on main. Initialize fast to an empty list and assert a standard-speed group is saved, without relaxing existing assertions. * fix(access): retain legacy LAN access when the key store cannot be created Allow only the configured legacy credential before either migration marker exists. Refuse revoked mirrors, disabled matches and unreadable stores; keep the fallback's caller identity stable when migration later succeeds. Cover read-only configuration directories, remote credential transports and revocation. * fix(backup): save settings before replacing gateway credentials Leave the key store untouched when settings validation or writes fail. Restore the previous settings association when the key store refuses its write, and report a rollback failure separately. Cover invalid settings and read-only settings/store failures. * fix(gui): reset missing caller filters and focus key controls without scrolling * test(provider): synchronize Zhipu quota fixture observations |
||
|
|
c0f3fa012a |
usage: combine gateway and local session requests with model charts and account labels (#239)
* usage: Requests lists the agents' own session-file calls, put to the vendor and account their files prove, charts them by provider, agent or model, shows what was said, and the tray panel gets a Usage tab The Usage page's Requests tab now covers requests an agent sends with its own sign-in (Claude Desktop's Code tab and Cowork, Claude Code, Codex), which never pass the gateway, and shows more of every request: why it failed, what was said in it, who it was of. Requests tab: a strip of four totals (tokens, requests, cost, cache hit rate); the trend of one metric — tokens, cost or requests — as columns by the hour, day or week, told apart by provider, agent or model (both remembered), beside a ranking of the same that is its legend and a way in (a click lists only that provider's or agent's requests; a provider picker sits beside the agent's). The ranking is as tall as the chart and scrolls in itself, with no scrollbar: a slim rail in the card's margin shows how much there is and where it is (its thumb dragged, the rail clicked), and the edge with more beyond it fades; under the chart (860px and narrower) it shows whole. A row opens to its details: the vendor's error type and words, request id, endpoint, and what was said in it (input and output, read from the agent's session file when opened, the call that ended nearest the request — nothing stored). A refresh period (off / 5 s / 10 s / 30 s / 1 min) and refresh-now. The Overview says it counts gateway calls only; Requests and the panel say they count both. The tray panel gets a Usage tab (today / 7 / 30 days, provider picker, four totals, a small chart, top five, "Open Usage"), and is as tall as its tallest tab (#124). Provider and account of a session-file call: never magpie's "claude" or "codex" subscription. Anthropic's when Claude Desktop's session metadata (not Claude-3p) names the account and organization, with that account's email; OpenAI's when Codex's rollout names a provider that is OpenAI's in config.toml — the built-in "openai", or a named one at OpenAI's address or signed in with the ChatGPT account and no base_url (requires_openai_auth) — with the creator account's email when the file records it. Anything else is "Local session", its recorded provider id and session account kept (CSV: session_provider, session_account). The config read is today's: a file names the provider id only. Gateway: a failed call keeps the vendor's error text and type, request id and endpoint; a Claude subscription's failure uses the status Claude Code reports (api_error_status). A request turned away before any vendor was asked is logged, marked rejected, listed in Requests and left out of every total. The client's own session header is kept as native_session beside X-Magpie-Session, and a session-file call is matched to a gateway record by request id, then by that session, equal tokens and an end within 2 s, only when unique both ways. Reading: session-file calls live in the session index main keeps on disk, parsed incrementally and outside its lock (Claude Code, Cowork in both Claude folders, Codex); the usage log is read on from where it was; a page builds the ledger once. Days are counted on calendar dates (DST). CSV gains request_id, endpoint, error_message, error_type, source, session_provider, session_account. i18n: one "Endpoint" (终结点), which a second key had turned for Azure's field. Tested: go vet ./..., go build (also GOOS=linux/windows, -tags nogui) and go test -tags nogui ./... pass. The whole GUI suite in Chromium and WebKit, en and zh (Playwright 1.62.1): all 393 tests pass. On this computer's files (7 days): 3,330 Claude Desktop calls resolve to Anthropic with the account, 1,991 Codex calls on a named ChatGPT-signed-in provider to OpenAI (620 with the account; older rollouts don't record it), 9 Claude Code CLI calls stay Local session. Co-authored-by: yetone <yetoneful@gmail.com> Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * usage: a session-file call of one of magpie's own Codex or Claude accounts is told as that provider, beside the gateway's calls on it — "OpenAI" and "Codex" (or "Anthropic" and "Claude Code") read as two vendors when they were one subscription Codex: an official route (above) whose creator account and user are one of magpie's Codex sign-ins (the CLI's own or a saved one) is magpie's "codex", with that account's email as the gateway's rows have it. Claude Desktop (not Claude-3p): an account and organization that are one of magpie's Claude sign-ins is magpie's "claude". Only while magpie has that provider signed in; another account, a rollout with no account recorded, or an ambiguous workspace stays OpenAI or Anthropic, and a relay stays Local session. Tested: TestSessionCallsOfMagpiesAccountsAreItsProviders (the account matched, another account, none recorded, magpie's account through a relay, Desktop in magpie's and another organization, Claude-3p, magpie signed out) and TestLedgerTellsCodexSessionCallsAsMagpiesCodex (a gateway Codex call and a session call of its account one provider of two calls, another account's OpenAI). On this computer (7 days): 3,439 Claude Desktop calls are magpie's Claude, 626 Codex calls its Codex, 1,322 older Codex rollouts with no account stay OpenAI. go test -tags nogui ./... and the usage GUI tests pass. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * fix: 修复请求统计缓存膨胀与会话账号误归属 #239 调用明细改为按会话文件分片保存并限制内存缓存，汇总索引仅保留统计数据；网关日志按需读取。 严格匹配订阅账号与用户 ID，排除自定义渠道、非官方端点覆盖、外部 CODEX_HOME 及关闭的供应商。补齐零 token 失败去重、Codex 原始会话 ID、拒绝标记导出和面板显示修复。 通过全量 Go 测试、静态检查、受影响模块的并发检查、52 项浏览器测试及 macOS/Linux/Windows 构建；使用 35 万条合成调用验证索引体积与内存改善。 * fix: 降低请求统计刷新与写入开销并明确本地账号展示 #239 请求分片改为追加帧和字符串去重，分页复用未变化的紧凑快照，采用 LRU 并移出全局锁内的磁盘读取。缓存 Cowork 目录，补齐同前缀改写检测及崩溃临时文件清理。 本地记录仅显示匹配账号或本地会话，明确官方登录标记与请求路由的区别。默认今日与模型维度，Auto Review 复用共享目录定价并单独标注估价参考。 完整 Go 测试、vet、相关 race 和 52 项浏览器回归通过；提供 2000 文件及四个大会话连续追加的可复现性能对照。 * fix: 优化用量徽标与耗时分级并保护分页边界 #239 官方登录、API、订阅和本地会话采用独立颜色与柔和底色，兼容明暗主题。耗时按 10 秒及 30 秒阈值着色，保留估算标识与原始毫秒提示；无有效耗时显示短横线。 限制分页选取范围，避免超大偏移整数溢出及越界空页的无效堆构造。补充阈值、徽标对比度和极端分页参数回归。 * fix: 将账号与来源徽标分为两行展示 #239 * fix: 提高用量表格模型文字对比度 #239 发送模型和已知实际模型使用主题正文次级色，表头与时间同步加深。保留缺失值弱化、转发提示和本地日志来源说明。Chromium 与 WebKit 的中英文、浅深色主题 10 项界面检查通过。 --------- Co-authored-by: yetone <yetoneful@gmail.com> Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com> |
||
|
Aliceandraper
|
02d501894b |
usage: link request accounting to routing history (#361)
Co-authored-by: raper <raper@raperdeMacBook-Air.local> |
||
|
Ns2Kracy
|
c900734020 |
feat(usage): account for upstream provider keys (#364)
* feat(usage): attribute gateway usage to individual API keys * refactor(usage): keep provider accounting focused on CLI and CSV * fix(usage): attribute System One calls and name upstream key fields explicitly * fix(usage): leave keyless System One requests unattributed |
||
|
yetone
|
49c98f40f5 | gateway: a Remote magpie records the agent that asked on the other computer (Jorben on Discord) — requests forwarded to a remote magpie went as magpie itself, so the remote's usage and routing said "magpie" for all of them. The forwarding magpie now names the agent and itself (X-Magpie-Agent, X-Magpie-Via), read only from a magpie User-Agent and stripped before any vendor; the remote records that agent with Via, and Requests shows "Claude Code · via office-mac". It is only a label: models, routing rules and the drift check still go by the real sender. TestRemoteMagpieAgent, TestLastSeenNotVia and usage-ledger.test.cjs fail without the change. | ||
|
yetone
|
c641c1da2d | usage: a built-in moved onto its plugin keeps one history per account (要保证插件订阅 provider 跟内置的订阅 provider所有逻辑都要一模一样) — the built-in's calls were kept as going to "dee@example.com" (or "api.factory.ai as dee@example.com"), the plugin's as "kiro as dee@example.com", so Usage split an account's model rows at the move, the older half as if the id had gone elsewhere. A subscription's calls are now told apart by the account they went as, the host only for the rest; records already kept group together with no rewrite. TestSummarizeKeepsMovedAccountTogether fails without the change. go vet, go test ./internal/usage pass. | ||
|
Comic Chang
|
901ee08280 |
Count usage at the configured provider/model price (#278)
Magpie reports models.dev's list price for every call. That is the right number for a vendor's own key and the wrong one for a provider that resells or exposes a model at a different tariff, and it leaves a model the catalogue does not list with no cost at all — a provider's own /models gives ids, not economics. magpie model price relay-a/gpt-5.5 0.12,1.20,0.01,0.15 magpie model price relay-a/* 0.12,1.20,0.01,0.15 magpie model price relay-a/gpt-5.5 --reset magpie model prices Absolute USD per million tokens. All four parts are required: a price missing one would understate the rest of every call, and a hand-edited file that left a part out would bill it at zero, so each part is a pointer and the setter refuses a price that is negative, NaN or infinite, naming the part at fault. Zero stays distinct throughout — a model served at no cost has a price, not the absence of one. A `<provider>/*` entry covers every model of that provider and an exact entry wins over it; --reset removes only the exact entry and says so when a provider-wide one is still in force. The order a price is looked for in is the price for this model, then `<provider>/*`, then the provider's own catalogue, then models.dev for the maker. A price is a provider's tariff, not the model's: the same model through two providers has two prices, and each keeps its own. A provider is resolved by its id, or by an id it was renamed from, and never by its display name — Find answers those too, and a record naming one was counted at another provider's price. provider.EffectivePrice is the one lookup every cost caller shares, so the usage ledger and a session's totals both go through it, and a session naming a model bare is still priced at its maker's list price, which is a different question from what one provider charges. catalog.PriceOf and PricedBy keep returning the models.dev price for anything wanting an unbiased number. The background-task pickers (draw, search, vision) still rank by catalogue price: they choose which model answers, not what a call is reported to cost. Unlike every other per-model preference this does not call catalog.Touched. What a call costs is not what an agent picks a model by, and the model lists magpie keeps in the agents' own files are not its to rewrite over a number in a cost report. A rename moves the prices with it through the walk #288 adds, so nothing here has to say so, and an id recorded before a rename still resolves. Validation happens where the entry is written, not in Save: one hand-edited bad price in the file must not make saving a theme or a window size fail. A price for a model the provider does not serve is refused the way `magpie model name` refuses the same id, since it is a price that never applies and nothing reports it as dead; a removal is exempt, so an entry left for a model that has since gone can still be taken away. |
||
|
yetone
|
1e9f3a46cb | usage: a Requests tab lists every request of the period, one row each, and exports them as CSV, from the window and from magpie usage --csv (Discord 范不着: a per-request ledger as sub2api keeps, to set beside the upstream's own bill) — the Usage page summed calls by agent and model, and the log did not keep the model the agent asked for or the one the reply said answered, so a single request could not be checked against a vendor's bill. usage.Record now keeps Requested (req, the model id the client sent, a magpie alias or group as it came) and Served (served, the model the vendor's reply named, only when it named one); every usage.Append in the gateway fills them (the relayed and translated paths, Codex's backend, image draws, decide), and records written before load as they did, without them. The swap test the Routing page uses (a dated or pinned name is the same model) moved to usage.Swapped so the ledger marks the same rows. usage.Ledger gives the period's records newest first with each one's list-price cost, the agent it is counted under and whether the model was swapped, filtered by agent, failures alone and a search over the models, provider, account, session and effort; usage.WriteCSV writes them (time, agent, requested_model, provider, host, model, served_model, swapped, effort, input, output, cache write, cache read and reasoning tokens, cost_usd, duration_ms, ttft_ms, status, error, session, kind). The Usage page gets a third tab, Requests (请求), between Overview and Sessions, under the same period picker: an agent filter, All/Failed, a search field and Export CSV over a table of time, agent, requested model, provider · account, model sent, served model (amber with the Routing page's sentence when another model answered, plain on a dated name, a dash when the reply named none), effort, in, out, cache write, cache read, cost, duration and status, a failure's row marked by a red dot and bold code; the totals over it and 100 rows a page with Newer and Older. GET /api/usage/requests serves a page, POST /api/usage/requests/export saves all the filtered rows to Downloads (never over an earlier file) and opens the folder, GET /api/usage/requests.csv hands a browser the file in magpie web. The table scrolls sideways in its own box; at the window's narrowest the words after the head's cost give way so the three tabs fit without the page scrolling sideways. No border stripe; clicks move nothing (the pager held where it was). en and zh strings together. Tested with TestLedger (order, cost, swap, a dated name, an old record without the fields, each filter, the CSV exactly), TestServedModelRecorded and TestServedModelUnnamed (a request through a fake upstream answering with another model records Requested fake/sol, Model sol and the served name; one naming none leaves Served empty), TestUsageCSV (magpie usage --csv, a period, a stray argument refused), TestUsageLedgerRoutes (paging, totals, filters, export to Downloads twice) and a new internal/gui/tests/usage-ledger.test.cjs in Chromium and WebKit, en and zh, light and dark: the tabs and columns, the swap tag on the swapped row only, the 429 row, Older and Newer over 130 requests with the pager left where it was, the agent, Failed, search and period filters asking the server from the first page, Export CSV posting the filters with no page and saying where the file went, at 560 wide no tab scrolling the page sideways and the cost uncut, no left border. go build -tags nogui (and GOOS=linux, GOOS=windows), go test -tags nogui ./... and the whole GUI suite (122 tests) pass. Not tried in the real window through Wails or against a live gateway's log. | ||
|
yetone
|
6aa99ef1c0 |
usage: costs show in RMB at a live rate, when Settings picks it (#212 L1cardo: 添加费用用人名币结算的选项，最好是能根据实时汇率来计算) — the Usage page, the tray panel, the TUI and the CLI all price a call in USD, magpie's list prices being dollars; Settings now has a Currency row (after Usage shows) offering $ USD, kept by default, and ¥ CNY, which converts every one of those at display time only — usage.Totals.Cost and the JSONL records it comes from stay in USD always, and a vendor's own balance (already in its own currency, a relay's ¥) is never touched.
The rate is internal/fx: a free, no-key endpoint (open.er-api.com/v6/latest/USD), cached in memory and in a small file beside magpie's other caches (XDG_CACHE_HOME/magpie/fxrate.json) for 12h, refetched only once that's stale, and falling back to the last rate it ever had — or a fixed 7.2 — while offline; the currency row's tooltip names the rate and when it was learned. usage.FormatCost carries the $/¥ formatting (2 decimals above $1, 3 below, whole numbers above 100) that usage_cli.go and internal/tui/pages.go used to each have their own copy of; both now read Settings' currency once per command/redraw rather than per row. internal/gui/api.go exposes the rate on /api/settings always and on /api/state only when cny is actually chosen, so usd users' hot path never touches the network for a rate nothing shows with. Tested with new internal/fx/fx_test.go (a fake server: fetches and caches, answers from memory then from the cache file with no further calls, refetches once stale, falls back to a stale cache or Fallback when offline, ignores a reply with no CNY rate), TestFXInState in internal/gui/fx_test.go, TestFmtCostShowsChosenCurrency in internal/tui/usage_test.go, and a new internal/gui/tests/currency.test.cjs in Chromium and WebKit, English and Chinese (the Usage page's $ by default and ¥12.34×7.2 once cny is picked, the currency row's labels/state/tooltip, a real wheel scroll deep into Settings left alone by picking a currency, the choice surviving a reload). go build -tags nogui, GOOS=linux and GOOS=windows builds, and go test -tags nogui -count=1 ./... all pass clean. A fetch that failed is not tried again for 10 minutes (the stale or fixed rate shown at once meanwhile), so offline each state() does not wait up to 4s on the network: TestGetDoesNotRetryAFailedFetchAtOnce. |
||
|
yetone
|
f9c99cf370 | gateway: a call Codex makes for itself says so on the Routing page, and goes to a pool account with what Codex says about it (碳碳双键: 为何 codex 桌面选的 5.6sol，但是请求记录…显示的全是 gpt-6-luna) — magpie changes no model: Codex sends its own calls on Luna (the guardian review of an approval, x-openai-subagent: guardian; a thread's title; memories) and, on Luna Reserve once the plan's allowance is used up, every turn with x-openai-codex-luna-reserve. Relayed to Codex's own sign-in these headers went on as they came, but a turn the pool of Codex's accounts served was signed afresh and went without them. Now x-openai-*, x-codex-* (turn metadata, installation, window, parent thread), session_id, conversation_id, x-client-request-id and version go on with it too; never a sign-in (Authorization, chatgpt-account-id, anything with authorization in its name) nor Codex's device attestation, the pool account's own going in its place, nor what holds for Codex's own account alone (x-openai-codex-luna-reserve, as another account's allowance may be left, and x-codex-turn-state, the backend's routing of the turn for that account). The trace, the Recent calls and the usage log keep the call's kind (kind, from x-openai-subagent; memgen; luna_reserve), and the Requests list, a replay and the request's story show it as a grey tag by the model — Approval check / 审批判定, Title / 标题, Memory / 记忆, Subagent / 子代理, Review / 审查, Compaction / 压缩, Luna Reserve / Luna 储备, an unknown one as Codex names it — the story saying Codex made the call itself and picks its model. The Requests list's model column fits its content (up to 36%) so model and tag keep their room, the tag giving way first. Tested with a fake ChatGPT backend on the pool path (acct-1 used up, acct-2 answering: both get the headers and neither the client's sign-in; fails without the change), callKind/codexHeader cases, and a new internal/gui/tests/routing-kind.test.cjs in Chromium and WebKit, en and zh (tags, the model shown whole, the story, a click leaving the row where it is); the other GUI tests, go build -tags nogui, GOOS=windows go build and go test -tags nogui pass | ||
|
yetone
|
d924802de5 |
usage: a streamed reply's time to its first token is kept, and its first text's (#196: usage 记录首字延迟（TTFT），用于计算模型的真实生成速度) — usage.jsonl had only a call's whole ms and its out tokens, so how fast a model writes couldn't be told from how long it waited or thought. The reply is now read as it goes to the agent, in the agent's protocol whatever the vendor spoke (Anthropic content_block_delta text/thinking/input_json and a tool_use's start, Chat content/reasoning_content/reasoning/tool_calls, Responses output_text/reasoning/function_call_arguments deltas and a function call's start, Gemini parts), and each record gets ttft_ms to the first content and first_text_ms to the first text, counted from the request as ms is, so ms − ttft_ms is the writing time; a reply that isn't streamed gets neither, and omitempty leaves old records as they were. Only the stream's events up to its first text are read (a JSON reply, or past 8 MB, not at all). Each try in the routing trace keeps its own from when it was sent, so a group that fails over shows which member was slow, and the route, the request log and the Codex backend's relay keep them too. Shown on the Routing page (TTFT in the list, first token / first text / tok/s in a try's story), in the Gateway's request log, and on the Usage page and in magpie usage per model as the mean TTFT and tok/s = out ÷ (ms − ttft) over the answered streamed calls. Tested with fake vendors streaming a gap apart for Anthropic, Chat and Responses, as they came and translated (Chat from Anthropic, Responses from Chat), the ChatGPT backend without a Content-Type, a whole reply, a group whose first member fails (its try untimed, the second's timed from its own start, the request's including the failed try), each protocol's events and split writes, and the summary's sums; the GUI's browser tests pass
|
||
|
yetone
|
a1ca00d31b | routing: a request shows the reasoning its model was actually sent at (显示意图路由实际的推理强度 #144) — the trace keeps the effort the agent asked for and, on each try, the one sent upstream after the turn's pick and fitting to the model's levels (picked marks the turn's pick), so the Routing list reads "Fake · m-big · high", its tooltip says what the agent asked for, and the request's story adds "The turn's pick replaced the medium Codex asked for."; usage.jsonl records the sent effort too, and the Usage session list shows where magpie routed a session's calls and at what reasoning ("→ m-big · high +1", with a Routed line per model and effort in its detail) | ||
|
yetone
|
8dae6aa25b | usage: each call is kept with the session it was part of — the X-Magpie-Session header when the caller sends one, else the session its agent names itself (Claude Code's x-claude-code-session-id, Codex's session_id, OpenCode's) — as "session" in usage.jsonl, and magpie usage lists the sessions that used the most, so several sessions on one model can be told apart | ||
|
yetone
|
c4268e524f | providers: a provider's id can change — its editor has an ID field (magpie provider set <id> id=<new> in the CLI), and renaming it moves what named it by the old one: the agents on its models (each spelled its own way, recorded as magpie's), the routing groups' members, rules and classifier, other providers' fallbacks, which agents are shown it, and the vendor's fetched list. The old id stays with it, so an agent still running on the old config reaches it, a profile saved before applies to the new id, and its usage so far is counted under the new one. Asked on Discord | ||
|
yetone
|
4790c06b02 | usage: each call keeps where it went — the provider's host, or the account it was — so a provider id later pointed somewhere else no longer puts the earlier place's tokens and cost under the new one: a model's usage is told apart by host (provider/model @ host) when its provider went to more than one place in the period, or to somewhere other than where it goes now. Asked on Discord | ||
|
yetone
|
04302b1e63 | agent(codex): a Codex taken off magpie behind its back says so, with Apply again — something else rewriting config.toml (another switcher, an installer, a profile of its own) left the row showing a magpie model while Codex asked OpenAI for it, and the user blamed magpie; magpie now remembers what it set on each agent (applied.json) and tells three kinds of drift apart: the wiring gone (the provider table, catalog or base URL, or a profile overriding them), a magpie model replaced by one of Codex's own, and a Codex used since with none of its requests reaching the gateway (history.jsonl against when the gateway last saw it — an old process on an old config). A drifted row carries a coral Apply again pill on its name's line (a badge on the logo in the panel), the reason in its tooltip, Keep current settings in the row menu; the window asks /api/drift every 15s, so it shows without a reload | ||
|
yetone
|
a9e1a6769a | agent + usage: each agent says what its User-Agent begins with, beside its name and icon, and the gateway tells requests apart by that — usage kept a list of its own, which had to be kept in step with the agents by hand and wasn't (DeepSeek Harness, omp and Command Code were missing from it, so they were drawn with no logo); a new agent is now known by its requests as soon as it is described | ||
|
yetone
|
658d264e14 | usage: DeepSeek Harness, omp and Command Code are known by their User-Agent — deepseek-harness/… was kept as it came, not as the agent dsh, so the Routing view and Usage drew it as an unknown agent with no logo; records kept that way are read as the agent's too | ||
|
yetone
|
829d52f75a | provider: a custom provider can name several catalogs (catalog=openai, deepseek) — a gateway reselling many vendors gets names and reasoning levels for all of them, prefixed ids like deepseek/deepseek-chat included (#17) | ||
|
yetone
|
402a96c39d |
Rename dial to magpie, with a magpie for a logo
The product, module path (github.com/yetone/magpie), binaries, env vars (MAGPIE_ADDR, MAGPIE_DEV_UI, MAGPIE_THEME, MAGPIE_DEBUG), config and cache folders (~/.config/magpie, ~/.cache/magpie), bundle id (com.yetone.magpie), gateway provider id and token, and every UI string now say magpie. On first run magpie copies ~/.config/dial and ~/.cache/dial to the new folders when they don't exist yet (copy, not move, so a still-running dial keeps working; the old folders can be deleted by hand later). The logo is a small round magpie in profile: one path for the header and the tray, and the app tile adds the white belly and the blue-green tail. The header mark is drawn in ink rather than the accent colour, which fought the text in light mode. |
||
|
yetone
|
30c489a000 |
usage: a token statistics page
The gateway now records every call's token counts (read from the provider's own usage block, in both the translated and the pass-through paths) with the calling agent taken from the client's User-Agent, into ~/.config/dial/usage.jsonl. A Usage tab sums them by period, agent and model, with a per-hour/day/week timeline and cost at models.dev list prices; dial usage does the same in the terminal. Also nudges the window header 1pt up so the brand sits level with the traffic lights, and lets ?view= open the window on a tab. |