0 Fork 0

T

wizzy-yangandwizzy-yang e5e87d980a 支持 Ante：把 magpie 作为 provider 写进 ~/.ante/catalog.json (#1210 )

* agent: Ante takes magpie as a provider in ~/.ante/catalog.json

Ante (antigma.ai, AntigmaLabs/ante) is asked for in #1179. Its catalog is
~/.ante/catalog.json ($ANTE_HOME moves the folder), merged on top of the
providers it ships: a providers map keyed by the id --provider takes, each
with base_url, wire_style (AnthropicMessage, OpenAiCompatible, OpenAiResponse
or Gemini), an optional auth, and preferred_models, the ids its model picker
shows (docs.antigma.ai, reference/catalog-reference). magpie adds the entry
"magpie" at the gateway's /v1 on OpenAiCompatible, which is the wire style
Ante speaks Chat Completions with and what the gateway takes every model on,
and lists magpie's models in its preferred_models. The user's own providers
and the models section are left as they are, and magpie's entry goes again
when magpie steps out; a file magpie made goes with it.

No auth block is written. The gateway listens on loopback and lets any token
in from this machine (gateway.Token's own comment, lan.go's identifyCaller:
"Loopback takes any token"), and Ante counts a provider with no auth as
authenticated. A bearer env_key would mean putting the gateway's key into
Ante's environment, which the user would have to do themselves -- the same
decision Empryo's entry makes, which sends no key of the user's either. A
gateway shared on the local network is another matter, and the same one every
agent magpie wires has.

Two things are deliberately left off a model's entry. A routing group is not
told what it reasons at: which member answers, and what that member takes, is
the group's own to decide per turn, and magpieModels sets no APIs for a group
for the same reason. And support_vision is never written: Ante takes a model
as seeing images unless told otherwise, and what magpie knows is only as good
as a provider's own list -- a relay's models are often not described at all,
so writing false would have Ante drop the reader's images before the gateway,
which describes them to a model that can't see them itself
(provider.Described). No other agent magpie wires declares it either.

Ante ships macOS and Linux builds alone and suggests WSL on Windows, so the
Windows machine's Ante is usually the one in a distro: wslKinds gains it
beside Empryo, which also means the gateway address Ante is pointed at is the
one that distro reaches magpie on (place.base), and a distro not known to be
in mirrored networking gets the notice it already gets for the others.

TestAnte covers a user's own providers and models section kept as they are,
magpie's entry added and taken away, Sync repointing it, and a file magpie
made going again. TestAnteKeepsTheUsersFile covers a catalog magpie can't
parse costing magpie's provider and not the user's. TestAnteGroupSaysNoCapab
ilities covers a group declaring neither effort nor support_vision.
TestAnteEfforts covers the ladder: Ante's has no "none" or "minimal", its two
lowest, so both are its "min", and the rungs come out in Ante's order
whatever order magpie lists them in.

Tried with a real Ante 0.2.9 in WSL Ubuntu: magpie wrote the catalog, and
`ante catalog` then read 16 providers with magpie's among them, 39 models,
and Ante filled in support_vision: true for each itself. Ante then ran a real
turn through the gateway — `ante --provider magpie --model
group/auto-deepseek-v4-1-flash -p …` answered, and magpie's own usage log has
the request (ep /v1/chat/completions, req the group's id, served by one of its
members, out 10) — and so did a second model on another provider. The gateway
was reached over the Windows host's address from the distro (172.17.128.1),
this machine's own being on 127.0.0.1 alone, which is what notMirrored tells
the user about.

go vet, gofmt -l and go build (linux nogui, windows) pass. go test -tags
nogui ./internal/agent: 12 failures here, the same 12 on unmodified main (the
Windows ones AGENTS.md lists). ./internal/gui and ./internal/provider:
TestGatewayFixQuitsOnlyAMagpie, TestPurposeAssetMatchesUsage,
TestUpdateThatWontStart and TestLoginUsageClaudeAskedMeanwhile, all four on
unmodified main here too. docs/reference.md's adapter table gains Ante.

* agent: Ante keeps the user's own keys, reads ANTE_HOME, sends no effort it wasn't told to, and starts Ante on magpie (#1210)

Seven points from the review, each with a test that fails without it.

1. ANTE_HOME was in the file's own comment and in docs/reference.md but never read:
the path was fixed to $HOME/.ante, so a user who set it had magpie write a catalog
Ante does not look at. anteDir reads it through place.getenv, the way MiniMax Code
reads MINIMAX_DATA_DIR, so a distro's own ANTE_HOME - which magpie can't read -
still means ~/.ante there. "ANTE_HOME" joins agentenv.Vars so a sandbox clears it.

2. providers.magpie was written whole, so every key of the user's that magpie
doesn't write - the auth block a gateway shared on the LAN or reached from WSL
needs to send a key, http_headers, extra_body, stream_idle_timeout_secs,
thinking_display - went at the next sync, and an unchanged catalog was rewritten
every round. It goes through theirsKept and syncJSON now, as #1103 did for the
others: the user's keys in magpie's entry stay, preferred_models is magpie's list
alone, and a file that says the same as it does is left as it is.

3. The two files were written in separate steps, so a change that failed halfway
left Ante's catalog without magpie's entry and its settings still naming magpie.
Each field's Set and its Sync are wrapped in atomic(), as empryo, minimax and kimi
do.

4. The comment said Ante's "min" was the rung it sends no effort at, and folded
both magpie's "none" and its "minimal" into it. Ante's reference says what min is:
"OpenAI-compatible providers send the selected level as the same-named
reasoning_effort (min is sent as minimal)" - so min is a sent level, and magpie's
"none" has no rung of Ante's to fold into. Ante's "min" is magpie's "minimal"; a
model magpie knows only "none" of comes out as the empty list, which is Ante's own
way of saying it takes no effort setting at all.

5. The default was the highest rung the model takes, so every model magpie listed
ran at Ante's slowest and dearest level. No effort is written: "Omit for models
with no reasoning knob (Ante then sends no effort parameter and hides the effort
slider)".

6. Having magpie in the catalog never meant Ante used it. What a session starts on
is the provider and the model of ~/.ante/settings.json; with neither set Ante
"uses the first authenticated provider in catalog order", and Ante's own presets
come before magpie's entry - so while the user has any of those signed in, that is
the one picked and magpie is not. (Measured: nothing named in settings, two keyless
providers ordered aaa_other then magpie, and the request went to aaa_other's port;
settings provider=magpie and it went to magpie's.) magpie sets that pair now and
saves what it found there, so Disconnect hands it back; a provider the user picks in
Ante's own /providers while magpie is wired is theirs and stands, and Check says so
instead of keeping quiet. Ante's settings name the model apart from the provider, so
magpie writes the catalog id it put in preferred_models, un-prefixed, and reads a
bare id as magpie's only beside magpie's provider.

Tests lean on the package's own testenv, not a real ~/.ante.
TestAnteSyncKeepsTheUsersKeys is modelled on ad3b7fe5's
TestAirProviderWritesKeepCustomFields and goes both ways - sync and pick - and
wants an unchanged file to keep its mtime.

Tried with a real Ante 0.2.9 in WSL Ubuntu on this machine (Ante ships macOS and
Linux builds alone; there is no Windows Ante here). The strongest of these is the
whole of it: magpie's own Go code - ante(home).Connect(), then the model field -
wrote a catalog.json and settings.json into a temp folder, that folder was handed
to the real Ante as ANTE_HOME, and Ante ran a turn through it with no --provider,
no --model and nothing typed by hand.

- `ante doctor` read `home ok /tmp/ante-e2e` and `16 providers (1 authed), 108
  models` from ANTE_HOME, and magpie's entry came back with the base_url it was
  given: ANTE_HOME really moves the folder, and a base_url already ending in /v1
  is not doubled (the request went to /v1/chat/completions).
- What a session starts on is settings.json's provider, measured against two
  keyless providers each answering on its own port, so the logged port names the
  one Ante asked. Catalog ordered aaa_other then magpie, nothing named in
  settings: Ante asked 44331, aaa_other - the first authenticated in catalog
  order, exactly the review's "很可能选不到 magpie". settings provider=magpie: it
  asked 44220, magpie. settings provider=aaa_other: 44331 again, so a pick the
  user makes in Ante's own /providers overrules what magpie wrote, which is why
  stepping out leaves it rather than handing back the one magpie found. And with
  magpie the only authenticated provider, auto-detection does reach it - so the
  catalog entry is not useless, it is simply not enough while the user has any
  other provider signed in, which is every real install.
- What Ante sends for effort, from the same files: no reasoning_effort at all for
  a model with no effort written (item 5, as its reference says omitting it sends
  none); `--effort min` on a model sent `reasoning_effort: "minimal"` - Ante's min
  is magpie's minimal, exactly item 4; and a model Ante was told
  `"supported_efforts": []` for sent no reasoning_effort even when asked `--effort
  low`, which is what a none-only model now gets instead of a level that refuses
  it.
- The user's own keys inside magpie's entry are ones Ante reads, not decoration:
  `ante catalog` hands back the entry's auth, http_headers, extra_body,
  stream_idle_timeout_secs and thinking_display unchanged, and a bearer env_key
  there makes `ante doctor` count the provider as the one authed. That is item 2.
- The no-auth decision holds on Ante's side, isolated by doctor's counts: Ante's
  own presets alone read `15 providers (0 authed)`; a magpie with no auth block
  reads `(1 authed)`; the same magpie given a bearer env_key that isn't set drops
  back to `(0 authed)`; with the key set, `(1 authed)`. So an entry with no auth is
  authenticated and one that asks for a key the user doesn't have is not - writing
  an env_key, which the first version's comment considered, would have made magpie
  the one provider Ante refuses to auto-detect.
- Ante fills `support_vision: true` in for itself, as the PR's own note said, and
  a routing group declared with no capabilities at all still worked.

Not covered by that run: the stand-in server answered inside the distro, so this
proves Ante's config handling end to end, not a live magpie gateway relay (the
first commit's message records a real turn through one). Every probe used
ANTE_HOME into a temp folder; this machine's real ~/.ante gained no catalog.json
or settings.json.

What each fix failed without it, one test each: taking ANTE_HOME out ->
TestAnteHome "$ANTE_HOME ignored"; theirsKept out -> "the user's auth lost or
changed"; syncJSON out -> "an unchanged catalog was rewritten"; atomic out ->
"settings.json kept half of a change that failed"; the old min mapping ->
"anteEfforts([minimal high]) = [high], want [min high]"; a written default ->
"deepseek/pro: effort written"; settings never pointed at magpie -> TestAnte; a
model never written -> TestAnteModelField; Check left quiet -> "moved off magpie:
\"\""; handing magpie back over a pick the user made while wired ->
TestAnteKeepsWhatTheUserPickedWhileWired; never restoring the model ->
TestAnteConnectDisconnect "not put back"; Connect picking the model field instead
of magpie as provider -> "Connect left the user's model beside magpie's provider";
ANTE_HOME kept out of agentenv.Vars -> TestFolderVarsAreListed. Taking
preferred_models out of the whole list is the one mutation no test turns red on:
mergeTheirs cannot merge a JSON array (sync.go returns want for it), so the file
behaves the same either way and the argument is there for intent and for the other
keys, not for behaviour.

go vet ./... and go build ./... pass, as do GOOS=linux go build -tags nogui ./...
and GOOS=windows go build ./..., and gofmt is clean on LF content (this clone has
core.autocrlf and no .gitattributes, so gofmt -l reports every file).
go test -tags nogui ./internal/agent fails twelve tests, and an untouched worktree
of origin/main run the same command on this machine fails the same twelve, test for
test; ./internal/agentenv, ./internal/appdir and ./internal/edit pass, and every
Ante test passes at -count=5. The whole ./... was run on both: the failing sets are
alike, origin/main having one more, TestLoginUsageClaudeAskedMeanwhile, already
filed as #1228. None of those twelve is this change's, and none is fixed here.

* docs: agent-wiring records that Ante keeps the user's keys in magpie's entry and starts on settings.json's provider (#1210)

The two rules the review asked for, written where the repo keeps them - the same lines ad3b7fe5 (#1239) added for Air and 2d9db1b6 (#1242) for malformed configs. The Verification block gains the package's own Ante run, as #1239 added Air's.

---------

Co-authored-by: wizzy-yang <wizzy-yang@users.noreply.github.com>

2026-10-08 16:58:41 +08:00

.github

ci: the GTK and WebKitGTK install on Linux gives up after 15 minutes, where a stuck apt held main's Test run for 2.5 hours (b0d456c3) and every later push queued and was replaced behind it

2026-10-08 06:02:22 +08:00

build

ci: the gateway's race suite runs over one process per core, not one at a time (wizzy-yang, #923 )

2026-10-05 23:54:03 +08:00

docs

支持 Ante：把 magpie 作为 provider 写进 ~/.ante/catalog.json (#1210 )

2026-10-08 16:58:41 +08:00

internal

支持 Ante：把 magpie 作为 provider 写进 ~/.ante/catalog.json (#1210 )

2026-10-08 16:58:41 +08:00

site

context: magpie inspects the context window of every request, session and agent

2026-10-08 05:36:17 +08:00

.dockerignore

docker: a server image and a multi-arch build workflow (#245 )

2026-09-30 03:21:19 +08:00

.gitignore

dev: a Go change under make dev rebuilds and restarts only the backend — the API and the gateway — behind windows and a tray that stay up, and the page refreshes what it shows in place, keeping its tab and anything open; a build that fails leaves the running backend be (build/dev.sh)

2026-09-25 01:14:56 +08:00

account_cap_cli_test.go

provider: a subscription account can be capped at a share of its usage windows, and routing treats it as used up there (Discord: hold a new Claude account at 70% of its five hours and its week to keep its ban risk down, and let magpie go on to the other accounts) — an account's cap (1–99, keyed by the provider id and the account in lower case, AccountCaps in providers.json beside AccountModels and AccountProxies) holds it once any window that applies to the model is at or past the cap and hasn't reset (Allowance.CapHeld; Aside windows and windows kept for another model are left out). One share for every window rather than one per window: the windows an account has differ by vendor (five hours and week for Claude and Codex, a month or a day for others, per-model weeks), the request was one figure for both, and a lower share for one window would be set by lowering the cap. The gateway's perKeyBarred moves a capped account to the candidates left out (barredOf marks it Capped with its use and when it is back, so the routing trace says "held at its 70% usage cap"), so groups, fallback, Ordered and Spread routing and the Codex/Claude Code switch list (NextLogin: a capped account is moved off, not returned to, and isn't a spare) all go on to the next account; a pinned capped account and a draw over only capped accounts answer 429. When every account that serves the model is capped, the client is turned away as when all are used up — 429 rate_limit_error with Retry-After at the soonest reset — and told the cap was reached, which accounts, at what use and cap, and how to lift it. A cap never spends a Codex reset: weekUsedUp, usedUp, BackAt and spendExpiringNow still go by ChatGPT's own 100%, so an account held at 80% with auto reset on is held and nothing is spent; a lone Codex account with a cap goes through serve() instead of being relayed as it came (codexAccounts), so the cap holds it. The Providers page shows a cap pill on each account's row (on hover until set) that opens the app's own menu — No cap, 50/60/70/80/90%, Other… (typed inline, focused without scrolling) — posting provider/accountcap; each window's bar gets a tick at the cap (from the right when the bar shows what is left), and an account held by its cap says so and until when. zh strings in i18n.js. CLI: magpie provider account-cap <id> [account [percent|off]] shows or sets caps. Tests: TestCapHeld, TestCapReached, TestParseCap; TestCapNeverSpendsACodexReset (80% windows, 70% cap: not used up, no reset due, routing held); TestCodexSwitchedAtCap (the active account at 75% with a 70% cap is switched off to the one at 20%, not back while capped, back once lifted; 100 and an unknown account refused); gateway TestAccountCapMovesOn (first account at 75% capped at 70%: the second is tried and the trace says 75/70; lifted: the first), TestAccountCapEveryAccount (429 rate_limit_error naming both caps, nothing sent, logged 429) and TestAccountCapSpendsNoCodexReset (one account at an 80% week, auto reset on: 429, nothing tried or spent; lifted: 200, nothing spent) — the three gateway tests fail with the cap check taken out; TestAccountCapCmd; account-cap.test.cjs (webkit, en and zh: pill, menu, Other…, No cap, cap ticks, held note, no <select>, no border stripes, no scroll on click). account-models, click-scroll, keep-login, codex-auto-reset, account-return, routing-blocked, routing-account-order, routing-quota-left, routing-auto-reset, routing-manual, quota-pools, quota-families and usage-accounts GUI tests pass in webkit. go vet, builds (darwin, GOOS=linux, GOOS=windows) and go test -tags nogui -count=1 ./... under a temp HOME pass. Not tried with real accounts; a cap acts on usage as last read, so a burst between reads can run a little past it.

2026-10-04 10:18:50 +08:00

account_concurrency_cli_test.go

gateway, gui, cli: each account or key can have its own limit on requests at once, with a bounded queue that turns requests away with a 429 (#892 , margbug01) — a provider's Concurrency applied to every key and account alike, the queue past it had no bound and no wait, and nothing showed what ran or waited. A key or account now may have its own limit over the provider's (Provider.AccountConcurrency, by lowercased account or KeyID; 0 none; unset takes the provider's, as before), counted in one lane across every model, routing group and agent. A provider's Queue size bounds how many wait for each of its lanes (one more is turned away at once) and Queue wait how many seconds one waits (then it leaves the queue); both 0 by default, as before. A request turned away goes on to the next key, account or group member without resting anything, else gets a 429 in its API's own shape (Anthropic rate_limit_error, OpenAI's, Gemini's) with Retry-After: 1, saying the limit and the queue. A slot is given back when the reply is read to the end, fails or the agent goes away; a waiter that goes away leaves the queue, and one granted as it gave up hands the slot on. In a routing group, or among a provider's keys and accounts, a full one gives way once to another with a free slot now, so a group spreads before anyone waits; a fallback provider is never asked for want of a slot, and with all full the request waits for the one routing chose. The Claude subscription path and plugin providers take their slot the same way, around the attempt; a parked Claude Code tool turn has already answered and holds none. GUI: each account and key row has a pill — "1/1 running · 2 queued" while requests are out (GET /api/lanes, read every two seconds and written into the pill in place), else its limit; none set shows on hover only — opening the app's menu (provider's, no limit, 1/2/3/5/10, Other… typed in place), posting provider/accountconcurrency; the editor has Queue size and Queue wait under Concurrency. CLI: magpie provider account-concurrency <id> [account|key [n|off|default]] and magpie provider queue <id> [size [seconds]]. en/zh/ja/de. TestAccountLimitSharedAcrossGroups, TestQueueFullAndWaitedOut, TestLaneReleasedOnFailure and TestFullMemberGivesWay (pass with -race, with TestMaxConcurrency and TestLanesLimitLifted), TestLaneLimitRoutes and TestAccountConcurrencyCmd are new and fail without the change; lane-limit.test.cjs (WebKit, en and zh: a key's busy/queued pill updated in place from /api/lanes, set from the menu, provider's posts null, Other… typed, an account's own limit, none on hover only, queue fields saved and refused out of range, labels on one line, every string in zh/ja/de, no select, no scroll, no left border) fails without the change. key-weight-fit, account-cap, provider-concurrency, click-scroll, account-models and api-key-usage pass in WebKit; the other WebKit failures fail the same on main. go vet, go build (darwin, GOOS=linux nogui, GOOS=windows) and go test -tags nogui ./... under a temp HOME pass.

2026-10-05 18:53:16 +08:00

account_models_cli_test.go

providers: each account of a subscription, and each key, can be kept for some of the provider's models only (#474 : 增加账号级别的模型选项, a low-quota but verified account kept for the cheap models) — every account or key a provider had served every model it did, so one couldn't be spared for some. An account's or key's row in its provider's editor now has a models badge: a click opens the provider's models as chips, Save keeps the account for those picked, All models gives it every one again; one kept for some says how many, always shown. magpie provider account-models <id> [account|key [models…|all]] does the same and lists them. It is kept in providers.json as accountModels, an account by its name in lower case, a key by its id; one not in it serves every model, as before. The gateway never sends a model to an account or key whose list leaves it out, in every routing mode, in drag order, in a group and as a fallback, and never falls back to it all the same; the trace says it was left out as set to serve other models. When every account or key there is leaves the model out, the request is refused with a 403 saying so and how to change it, not "none of X's models is ready". TestKeyModelsNarrowCandidates, TestAccountModelsNeverChosen, TestAccountModelsCmd and account-models.test.cjs fail without the change. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass; account-models, click-scroll, old-webkit, account-arrange, account-proxy, account-return, routing-account-order, panel-routing, unlisted-models pass.

2026-10-02 05:50:23 +08:00

accounts_cli_race_test.go

fix(accounts): separate usage deduplication from results (#641 )

2026-10-03 13:33:12 +08:00

accounts_cli_test.go

usage, gateway, gui, provider, cli: the tests pass when a run crosses midnight, and a usage answer reads the clock once (#1046 )

2026-10-07 02:14:29 +08:00

accounts_cli.go

provider, cli: a Copilot account is told apart by its host as well as its login, so one GitHub login on github.com and on enterprises' *.ghe.com is kept as separate accounts, none written over or dropped as the editors' own (#1220 )

2026-10-08 07:27:03 +08:00

accounts_copilot_cli_test.go

2026-10-08 07:27:03 +08:00

accounts_plugin_cli_test.go

test: TestAccountsOfAPlugin expects forgetting the account in use to put the other first — since 30d952cf (v0.1.976) forgetSideLogin no longer refuses the account a subscription uses first; magpie accounts forget goes through the same ForgetLogin, so a plugin's in-use account is forgotten and the remaining one becomes the one in use. Test-only; go vet and go test -tags nogui . ./internal/provider/... pass.

2026-10-05 15:39:43 +08:00

agent_default_cli_test.go

agent: Claude Code's model set back to its default puts back the endpoint and token the user had before magpie and leaves them (__jingling on X: 接入后跑 magpie claude model default，会把原来的 ANTHROPIC_BASE_URL 和 token 也删掉，之后再 default 也恢复不了，复现了两次) — the model field's default deleted every env key magpie writes, the user's own ANTHROPIC_BASE_URL and ANTHROPIC_AUTH_TOKEN among them, and forgot the stash that kept them from before magpie, so Disconnect after it had nothing to put back. It now takes magpie out as Disconnect does (its endpoint, token, tiers and window, the user's endpoint and token put back from the stash) and deletes only model; an endpoint the user set themselves, wired or not, stays, as the Agents page's default option (Claude Code · their host) says. magpie's env left at a gateway address since changed (its token) still goes. In a sandbox HOME with the release binary: settings.json with // mine, model opus, env ANTHROPIC_BASE_URL https://api.deepseek.com/anthropic and a token; magpie claude deepseek/deepseek-chat, then magpie claude model default: the comment, base URL and token back, model gone; magpie claude default after it leaves them. TestAgentModelDefaultKeepsTheEndpointBefore fails on the old code. go vet, builds (darwin, GOOS=linux nogui, GOOS=windows) and go test -tags nogui -count=1 ./... under a temp HOME pass.

2026-10-05 00:56:46 +08:00

AGENTS.md

docs: contributors.md says what stops a community PR's review for possible harm, what is closed unreviewed and when an author is proposed for blocking, and AGENTS.md links it

2026-10-06 03:50:07 +08:00

autostart_cli.go

termux: support Android builds and installation (#644 )

2026-10-03 14:29:32 +08:00

backup_cmd.go

cli: 新增 magpie webdav，在终端里开启、修改和触发 WebDAV 同步 / add magpie webdav to turn on, change and run WebDAV sync from the terminal (#127 )

2026-09-28 14:54:04 +08:00

browser_android_test.go

termux: support Android builds and installation (#644 )

2026-10-03 14:29:32 +08:00

CLAUDE.md

docs: LESSONS.md keeps what the nightly review of merged work finds, and agents read it before changing code

2026-10-06 03:10:24 +08:00

console_windows.go

Desktop app for Windows and Linux

2026-09-24 03:22:02 +08:00

Dockerfile

docker: the image has bash and busybox, so a terminal in the container opens (スライム on Discord: 这2天的docker版更新后无法进入terminal模式，导致配置不了devin … exec: "/bin/bash": stat /bin/bash: no such file or directory)

2026-10-05 03:23:18 +08:00

gateway_keys_cli_test.go

gateway keys: a key can be created with a value of the user's own, one their clients already send, so moving from another gateway (CLIProxyAPI's api-keys) doesn't mean re-keying every client (love1sbug on X)

2026-10-07 14:34:36 +08:00

gateway_keys_cli.go

2026-10-07 14:34:36 +08:00

go.mod

go: 1.26.8, whose race detector leaves a forked child alone before exec on macOS (#1184 )

2026-10-08 06:48:55 +08:00

go.sum

go.mod: go mod tidy — moejs is required directly (internal/gateway imports it), and go.sum drops testify 1.11.1 and go-spew/go-difflib, which nothing builds with

2026-10-06 04:01:01 +08:00

groups_cli_test.go

provider, agent, cli: a routing group's id carries Claude Code's [1m] mark (#1000 )

2026-10-06 16:02:03 +08:00

groups_cli.go

provider: one GroupIDOf reads a group's id from a ref, in place of five copies of the same CutPrefix(TrimSuffix(TrimSpace(ref), "[1m]"), GroupPrefix) — #1000 (6f391bc8) taught the [1m] mark to each group lookup by pasting the expression into AutoStandIn, GroupFinder and DisabledGroup in group.go, groups_cli.go and the agent's reseat.go; a sixth lookup would have to find and copy it again. Behaviour is unchanged. go test ./internal/provider/ ./internal/agent/ and the root package pass, as do the gui and gateway Group/1m tests; build and vet pass.

2026-10-06 16:27:51 +08:00

groups_effort_cli_test.go

routing: a group's member may be a model at an effort of its own, provider/model:low (#189 , @luw2007: model + effort 才是完整的组合项) — a member was only a model, reasoning as the agent asked or as the group's classifier picked, so "the same model, cheap and quick" and "the same model, thinking hard" could not both be in a group, nor could a rule send to one of them. A member now may carry an effort (none … max): a request routed to it is asked for that much reasoning whatever the agent asked or effort=auto picked, at the level the model has nearest, while the vendor is asked for the model's own id. The same model at two efforts is two members that rules (use=m:high), stickiness and the trace tell apart; an id whose own last part is a colon (a :free, :7b, :0) stays the model's. The group's reasoning levels are those of its members that follow the agent, and the editor has a reasoning button on each member. Tested with a fake provider through a sandbox magpie: the upstream bodies carry the fixed effort in Chat, Responses and Anthropic shapes, and the routing view shows m1:low / m1:high as two seats, light and dark

2026-09-29 13:45:29 +08:00

groups_fast_cli_test.go

routing: a group's member can be sent in its vendor's fast mode, beside its own reasoning (vs on Discord: a member "gpt-6.1 sol · high · fast") — a member's effort was already its own (#189 , "provider/model:effort") but there was no way to ask for speed, so a group could not hold "gpt-6.1-sol at high, priority" next to slower members. A group now lists in fast the members it sends fast, as Members spells them, kept beside Members rather than in their ids so an older version still routes to them, only not fast (checked: HEAD's build on the same providers.json sends the same members at their effort, no tier, and leaves the file as it was). When the gateway sends to such a member it asks in the upstream's own words, only where the model has a fast mode magpie can ask for (provider.CanFast): service_tier "priority" for a ChatGPT account's GPT models and an OpenAI key's GPT/o-series models on its Responses API, Cursor's -fast variant, and speed "fast" with the fast-mode-2026-02-01 beta for Claude Opus 4.8/5/5.5 on an Anthropic key (api.anthropic.com); a relay, Bedrock, a Claude subscription, a model without one, or a provider since moved off those hosts is sent untouched. It is applied in the agent's own API and carried through translation (parseAnthropic now reads speed), so Chat, Responses and Anthropic agents all get it. A translated request for OpenAI's Chat API is still told no tier (TestCursorPluginFast), hence the Responses requirement. The trace marks the try, the order and the group (fast), shown as "fast" beside the reasoning in Requests and the order. Typed, a member is provider/model[:effort]:fast: magpie group add/set models=… takes it, fast=<m1>,… sets them, models-= takes either spelling, and the group lists and shows members as typed with "· fast"; a model with no fast mode, or a group in the group, is refused. The GUI group editor shows a "Standard speed"/"Fast" toggle (标准速度/快速) beside a member's reasoning only for a model that has one, the card reads "· fast" after the reasoning, and fast follows a member's reasoning change and leaves with a removed member; the TUI's group view takes E to step a member's effort and F to toggle fast. Provider renames carry it. TestFastMemberOpenAI, TestFastMemberAnthropic, TestWithFastWire (gateway, per wire format, a fake vendor recording body and anthropic-beta), TestCanFast, TestSaveGroupFast, TestGroupMembersFast, TestGroupMemberEffortAndFast, TestGroupSaveFast and group-member-fast.test.cjs fail without the change. A sandbox magpie (own HOME, gateway on 3966) with providers at http://api.openai.com and http://api.anthropic.com through a local recording proxy sent priority+high to OpenAI and speed fast + the beta to Anthropic from Chat, Responses and Anthropic clients, and nothing extra for Sonnet or a non-fast member. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass; group-member-fast, click-scroll, old-webkit, routing-levels, routing-manual, routing-effort, settings-groups pass (Chromium, WebKit, en/zh).

2026-10-01 17:13:34 +08:00

groups_levels_cli_test.go

routing: a group can name the reasoning levels agents are offered, so one member with few doesn't take the rest from the others (#295 ) — a group offered only the levels every member has, so deepseek-flash (low/high/max) beside models with medium and xhigh left the group without them. Group.Levels (CLI magpie group set <id> levels=low,medium,high,xhigh, levels= clears; TUI l; GUI group editor's Levels: its models' shared / named) is offered instead in /v1/models, Codex's catalog, Pi and the rest; only levels magpie knows are taken, stored lowest first; a group in a group that names its own offers them for its models; unset is as before. A member without the level asked is sent its nearest, as it already was. The GUI's group save also keeps a family set from the CLI. TestGroupLevelsOverride, TestGroupLevelsReachAgents, TestGroupLevelsNamed (passthrough and translated: medium→high, xhigh→max on the low/high/max member, as asked on the one with all), TestGroupSetLevels and routing-levels.test.cjs (Chromium, WebKit, en/zh) fail without the change. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass (TestUserPath, a known flake under load, passes alone); click-scroll, old-webkit, routing-effort(-row), routing-levels, settings-groups GUI tests pass.

2026-09-30 16:26:37 +08:00

groups_pattern_cli_test.go

group: a routing group's members can be patterns, so a group follows a provider's catalog (#766 : magpie group add my-free-pool models='openrouter/*:free,opencode-zen/*-free') — a group names its models one by one, so a pool of a vendor's free models went stale as the vendor added and dropped them. A group now keeps patterns apart from the models it names (Group.Match): a glob, * any run of characters (/ too) over the provider/model id in any case, or re:<regexp> over the whole id. groupsIn, which every reader goes through (Groups, FindGroup, /v1/models, MemberGroups, GroupsWith, RenameGroup, rules, Off, Pick, the GUI, TUI and CLI), puts after the named models every enabled provider's model a pattern matches, in catalog order, deduplicated, the named one keeping its place; a pattern never matches a group. What was matched is derived (Group.Matched) and never stored: store() and SaveGroup keep only the named members, so a save never freezes matches. Off and rules may name a matched model. A group with only patterns is allowed; one matching nothing routes nowhere and says so: magpie group <id> lists each pattern with how many models it matches now ("matches nothing now" in amber), the group list and the TUI too, and the GUI card shows a line per pattern with its count. CLI: models= takes patterns among the ids, models+= adds them (naming a matched model moves it to where it is named), models-=<pattern> drops one, models-= of a matched model is refused naming its pattern; the help documents patterns. GUI: the editor has a Patterns box (Add pattern / Remove, validated as the server does), matched models follow those named marked "by pattern" with their off switch and no Remove, and saves send members without the matched ones plus match; zh strings added. Tests: TestGroupPatterns, TestGroupPatternMembersOffAndRules, TestGroupPatternMatchingNothing, TestPatternSyntax (provider), TestPatternGroupRoutes (gateway: a request reaches a matched model, a model a provider adds joins, Off on a matched one, /v1/models lists the group), TestGroupPatternsCLI, and group-patterns.test.cjs (WebKit, en+zh); they fail on the old code (the Go ones don't build, the GUI one finds no pattern lines). GUI: group-patterns, group-found-off, group-member-fast, group-member-off, settings-groups, agent-model-groups, remote-group-served, routing-manual pass on WebKit; group-from-model-add has the same 2 failures (600x420) as origin/main. A request to a group whose patterns match nothing now is a 404 naming the group and its patterns (emptyGroupError), not 'magpie knows no model' and every model; TestEmptyPatternGroupSaysSo. With the owner's real config under a sandbox HOME: group/ds-pool of models='deepseek/*' listed deepseek-flash and deepseek-v4-pro by pattern, stored only the pattern, was in /v1/models and answered from deepseek-flash; none-pool of 'nobody/*' said its pattern matches nothing. go vet, builds (darwin, GOOS=linux, GOOS=windows) and go test -tags nogui -count=1 ./... under a temp HOME pass.

2026-10-04 16:52:15 +08:00

groups_pick_cli_test.go

routing: a group can be routed by hand, its model picked on its card (#317 , @azir12345: pick the channel as CC Switch does) — a group's routing may now be Manual: every request goes to the one member picked (pick in the group's JSON; the first when none or one no longer in it), over that member's own accounts or keys, and the others and the rules wait (kept, not dropped) until another routing is chosen; none takes over when it fails. On Routing, a manual group's card lists its models as pills, the picked one marked by a dot (role radio), and clicking another saves the group with that pick without opening its editor or moving the page; its rules tag says they wait. The editor offers Manual beside the other routings. magpie group pick <id> <model> (or group set <id> pick=<model>, a bare model id when it names one member) picks from the CLI; magpie groups and group show mark the pick, the TUI shows "manual → model". A renamed provider or model renames the pick. TestManualGroup, TestGroupPick and routing-manual.test.cjs (Chromium, WebKit, en/zh) fail without the change. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass; click-scroll, old-webkit, routing-levels, routing-steady, panel-routing, settings-groups pass.

2026-09-30 19:42:44 +08:00

groups_rules_cli_test.go

fix(rules): reject nan/inf and overflowing token lengths (#877 )

2026-10-05 16:31:07 +08:00

groups_rules_cli.go

routing: a group's rule can hold hours of the day (Discord: send DeepSeek's or GLM's peak-price hours to another provider) — a rule takes time: {from, to, days} in this computer's local time, HH:MM to HH:MM; hours that end before they begin run past midnight and belong to the day they begin on (Friday's 22:00–08:00 takes Saturday's early hours), days are optional, and the hours are checked as a turn begins, so a turn that began inside them finishes where it went. The rule reads "time 09:00–18:00 Mon–Fri" on the group and in the trace; the editor types the hours into one pill (从 … 到 …), notes past midnight, marks a time that isn't one and picks days like the agents (every day, weekdays, weekends, or each); magpie group rule add … time=14:00-18:00 days=mon-fri and the TUI's rule line take it too. Older versions ignore the field, and a rule with only hours then matches nothing there. TestRuleTimeMatches and TestRuleTimeWindowAtTurnStart (injected clock) and routing-time.test.cjs fail without the change. A sandbox magpie with two fake vendors sent a request inside the hours to the rule's member and one outside them, or on another day, to the first. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass; routing-time, routing-compact, routing-manual, routing-steady, settings-groups, click-scroll, old-webkit pass.

2026-10-01 15:04:16 +08:00

gui_off.go

update: a restart to update from the open window (Windows, Linux) opens the window again, on the tab it was asked from, instead of the tray icon alone (#275 Aimer779: 设置页更新重启后主窗口消失，只剩托盘) — RelaunchBinary always started magpie tray, autostart's argument, so the new version came up as a tray icon however the update was asked for; the Mac reopens its .app and was fine. The window's Update pill and Settings' "Restart to update" send the tab they're on, the new process starts as magpie gui <tab>; the tray menu's Restart to Update brings the window back if it was open and keeps to the tray if not; autostart stays tray. magpie gui <tab> / magpie app <tab> open the window on that tab, and hand it to a magpie already running. The MAGPIE_REPLACES handover is unchanged: the new process waits for the old one before its single-instance lock. Tested with TestRelaunchArgs and TestRelaunchBinaryArgs (a script in magpie's place is started with gui settings <pid> / tray <pid>); go vet, go build (GUI and -tags nogui, GOOS=linux, GOOS=windows), go test -tags nogui ./... pass. Not tried: a real restart to update on Windows or Linux.

2026-09-30 12:33:36 +08:00

gui_on.go

fix(proc): end what a CLI probe started, on its timeout and when magpie exits (#414 )

2026-10-02 00:42:48 +08:00

healthcheck_cli_test.go

test: every package's tests pass on Windows, and none writes outside its sandbox (the user: 把 Windows 上那几个失败的测试修掉) — on a Windows box the suite failed in most packages, and the root package hung for 25 minutes. Tests set HOME, which os.UserHomeDir ignores on Windows (it reads USERPROFILE), so they read and wrote the runner's own home; each now sets USERPROFILE beside HOME, and Devin's, Goose's, Crush's and Claude Desktop's tests set APPDATA/LOCALAPPDATA, where those keep their files there. said() read the command's output only once it returned, and a pipe holds a few KB on Windows, so magpie model --help blocked forever; it reads while the command writes. Unix permission bits (the gateway key store's 0600 too), exec bits and symlinks Windows lacks are checked only off Windows; TOML strings hold Windows paths as literal strings, JSON as marshalled ones; a URL's path is compared as one. The provider and usage packages run in a home of their own (TestMain, as the gateway's already does), since a CLI's identity kept by a refresh still going when its test ended landed in the runner's ~/.config/magpie — and on a Mac in the user's own. Two product fixes came out of it: imagemcp took a file:///C:/… root or image for the path /C:/…, which doesn't exist on Windows, and now makes a Windows path of it (a host for a UNC share); and session discovery could keep a new Cowork session hidden on Linux, where a folder's mtime is a kernel tick and its size doesn't change, so an entry added within the tick of the last listing left both as they were — a listing made within 2s of its folder's last change is read again, as git does for racy files. TestFilePath and TestRacyDirectoryListedAgain fail without the change. On Windows 11 every package passes (32 of 32) and a run of each package in a fresh home leaves nothing in home, APPDATA or LOCALAPPDATA; on Linux (WSL) and macOS go test -tags nogui ./... passes. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build pass.

2026-10-01 23:15:07 +08:00

healthcheck_cli.go

settings, gateway: the gateway's port is set in Settings › Network › Gateway, and every agent magpie connected moves with it (Magic_zero on Discord: 能否添加自定义端口号 — 3425 is taken on their machine, and they want a port of their own that is easy to remember and tell apart)

2026-10-05 11:28:51 +08:00

LESSONS.md

docs: LESSONS.md gets the review of 10-07's commits — fix-the-class, re-derive, red-on-main and merge-record lessons seen a third day move into the code standards; not tried with the real thing seen a second day (b2345078→7837f90d, #1050 , cda11d84); positives from 6b6113aa, d40fee80, bed306ae and #948

2026-10-07 23:46:48 +08:00

library_cli.go

library: an RTK release winget or Homebrew doesn't have yet says "v0.51.0 is out · waiting for winget" with no Upgrade, until it does (#1025 , Fermin214)

2026-10-06 20:56:52 +08:00

library_rm_all_test.go

library: Remove all beside Turn all on/off takes every skill out of the library at once (#449 ) — a library of many skills could only be emptied a row's Remove at a time. Remove all, in red, asks in the page first, naming the agents that lose the skills, the projects magpie placed them in, the folders that go to magpie's backups and those of the user's own that are only unlinked; Cancel sends nothing. Confirming sends every name in one call, library.RemoveSkills, which takes each as RemoveSkill does, the folders kept aside together under one backup; one that can't be taken out stays, and is said, while the rest go. magpie library skill rm --all does the same, asking y/N on a terminal and, with none, only with --yes. TestRemoveSkills and TestLibrarySkillRmAll fail without the change, as does remove-all-skills.test.cjs (Chromium and WebKit, English and Chinese); click-scroll, old-webkit, every-skill pass. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass (bar the known Claude account flake TestClaudeSignedOut).

2026-10-02 00:47:15 +08:00

LICENSE

Open source under MIT; the site shows third-party models in every agent

2026-09-24 02:16:29 +08:00

main_test.go

Add German translation; harden paths against unset env vars (#770 )

2026-10-04 23:30:56 +08:00

main.go

tui: magpie tui serves the gateway while it is open when no other magpie does, so agents it connected reach it in WSL (gnayiab on X)

2026-10-05 21:29:01 +08:00

Makefile

Add German translation; harden paths against unset env vars (#770 )

2026-10-04 23:30:56 +08:00

model_cli_test.go

2026-10-01 23:15:07 +08:00

model_cli.go

catalog, gui: a 1-hour cache write is 2× input for a Claude model only, any other's unset is its 5-minute price and isn't shown (PAMI on Discord)

2026-10-05 22:55:30 +08:00

model_compact_cli_test.go

claude: a Claude model runs to its own window in Claude Code, not 272K, and magpie model compact on|off is the Long conversations switch from the terminal (Max on Discord: a [1m] model's context stopped at 272K, magpie wrote CLAUDE_CODE_AUTO_COMPACT_WINDOW back when it was taken out, and there seemed to be no way to change it) — on magpie, Claude Code was told CLAUDE_CODE_AUTO_COMPACT_WINDOW=272000 whatever its model, so a [1m] Claude model compacted at 272K, though Anthropic runs it to 1M (the cap was meant for other vendors' long windows: Chen's DeepSeek turns of ~550K). Now a main model that is one of Anthropic's Claude models, from whichever provider, has the env left out (magpie's own value taken away), and Claude Code compacts at the model's own window; another vendor's model of a longer window keeps the 272K cap unless Settings → Long conversations is on Full window. A value the user writes there is still kept. The switch was only in the app's Settings; magpie model compact [on|off] (alias full-context) shows and sets it, and the Settings row's description says how Claude models are treated (en, zh, ja, de). TestClaudeCompactWindow (a Claude [1m] model gets no 272000, set and synced; another vendor's after it is capped again) and TestModelCompactCmd fail on the old code. The Long conversations row read right in WebKit, en and zh. go vet, builds (darwin, GOOS=linux nogui, GOOS=windows) and go test -tags nogui -count=1 ./... under a temp HOME pass (TestClaudeFailureKeepsClaudeCodesStatus flaked once under load, passes alone).

2026-10-05 00:09:49 +08:00

model_price_tier_cli_test.go

catalog, gui: a 1-hour cache write is 2× input for a Claude model only, any other's unset is its 5-minute price and isn't shown (PAMI on Discord)

2026-10-05 22:55:30 +08:00

model_suffix_cli_test.go

models: Provider in model names has a third way, a name the user gave used just as they wrote it (#92 marsxxl: v0.1.591 的 Codex 下拉里自定义名称又带上了 · WorkBuddy / · Claude Code) — 559ce021 (#203 ) had a custom name keep " · <provider>" after it like any other, so "Opus 5.5" read "Opus 5.5 · Claude Code" in every list Labels feeds (Codex's model_catalog_json and the gateway's Codex /models, Pi's, OpenCode's, ZCode's, OMP's, Muse's), while #92 had been promised the name as written. Both are kept: the setting is now Off / Not on names I set (自定义名称不带供应商) / On. On stays the default and keeps #203 's behaviour, so nobody's list changes unasked; own leaves a name the user gave as it is and a vendor's name with its provider's; off is #335 's plain names. Stored as plainOwnNames beside plainNames, so a settings.json of before reads as it did (plainNames: true is off). POST /api/settings/plain-names takes mode on|own|off (a body of on alone still works), magpie model suffix on|own|off, a Settings save keeps it, and /v1/models' magpie_label now follows the setting through Labels as the agents' lists do. The row's hint is one line that fits (en, zh), and its zh name says 供应商 as the rest of the app. Prompts and headers are unchanged. TestSuffixMode, TestSuffixModesReachAgentFiles (Codex model_catalog_json and Pi models.json), TestModelsListSuffixModes (/v1/models magpie_label) and model-suffix-own.test.cjs (Chromium and WebKit, en and zh) fail without the change; TestModelName and TestModelNameAndLevelsReachAgentFiles keep #203 's assertions. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass (TestConfiguredModelsAdvertiseImageInput load-flaky, passes alone); plain-names, click-scroll, old-webkit pass.

2026-10-01 23:20:57 +08:00

omp_cli_test.go

agents: magpie omp auto sets omp's thinking to auto, and the panel's effort slider shows a level it doesn't list as it is (#339 )

2026-10-01 00:20:19 +08:00

plugin_key_cli_test.go

plugin: a plugin names its own icon and the key field's title and hint (Lemon on Discord) — a plugin's provider took only the market's icon, and an api method's key field always read "<name> API key" with no hint. auth.icon (or package.json "magpie": {"icon"}) as an https URL, fetched once through the public-only icon path, or a data:image URI now comes before the market icon; an api method's label titles the key field as in OpenCode, and a new placeholder hints it, in the window and in magpie plugin login. README has a For plugin authors section. TestPluginOwnIcon, TestPluginOwnIconAndKeyHint and plugin-key-hint.test.cjs (Chromium, WebKit, en/zh) fail without the change.

2026-10-01 11:42:45 +08:00

plugin_login_cli_test.go

provider: a plugin account signed in again is read afresh, not answered by the reading kept from the refused sign-in (TestPluginLoginTakesTheLapseOff red after its first run in a process)

2026-10-08 13:52:50 +08:00

plugin_middleware_cli_test.go

plugins_cli: magpie plugin off, on and rm take a plugin's short name, as options does (the owner, testing for real) — magpie plugin off think-tags answered no plugin "think-tags" while magpie plugin options think-tags found it, so the names the community READMEs and usemagpie.ai's docs write worked for one command only. installedName turns a short name (think-tags for @magpie-community/middleware-think-tags, plugin.ShortName) into the installed plugin's package name for on, off and rm; a name a plugin has itself, or one no plugin has, is kept as it was. Found and tested end to end in a sandbox HOME with a real DeepSeek account: Model Map and Think Tags installed by clicking Install under Plugins › Discover › Gateway middleware in the real app (from a local verdaccio registry holding the real packages, until their first npm publish; magpie built with npmRegistry pointed at it), an alias set in Model Map's Options editor served by deepseek-flash and named back, think-tags off by short name let the model's <think>…</think> through and on took it out ("51"), rm think-tags by short name and Model Map's Remove in the app left plugins.json empty and the alias unknown. TestPluginOnOffRmShortName is new and fails without the change. go vet, go build (GOOS=linux nogui, GOOS=windows) and go test -tags nogui ./... under a temp HOME pass.

2026-10-05 22:08:31 +08:00

plugins_cli.go

provider, plugins: a sign-in reads as done only once its account is listed again, and the command line's plugin sign-in brings the account back and takes its lapsed mark off (#1061 )

2026-10-07 06:24:24 +08:00

provider_plugin_cli_test.go

2026-10-01 23:15:07 +08:00

provider_refresh_cli_test.go

tui, cli: adding a provider says how many models its list had, or why it had none, and m (magpie provider refresh <id>) fetches the list again (akic404 on Discord: 还是tui cli问题，没有获取上游模型功能，新建之后模型数是0)

2026-10-04 01:24:47 +08:00

providers_cli.go

gateway, providers, gui: a model on this computer or the local network can be set to get requests unmasked by Settings' redaction (lc on Discord: 本地模型可以不脱敏)

2026-10-07 00:33:15 +08:00

providers_decide_cli_test.go

provider: Bailian's decision model as a routing preset, and System One for custom providers (#647 , Aimer779: Alibaba Cloud Bailian's decision-model-preview speaks TypeSafe's System One at POST <root>/systemone, and magpie only took it from TypeSafe's Jev) — a new preset, Bailian Decision Model (qwen icon, decide-only like TypeSafe Jev), asks decision-model-preview at its plan's root: Workspace · Beijing / Workspace · Singapore (https://{WorkspaceId}.<region>.maas.aliyuncs.com/compatible-mode/v1, the editor asks for the workspace ID and fills it in) or Token Plan · Beijing (token-plan.cn-beijing…, sk-sp- keys). Saving with the workspace still unfilled is refused, both in the editor and in provider.Add. A Bailian host has no /models for it, so its list is the one model, checked by a System One ask. A custom provider can now be a System One API: the CLI's decide=<root> (with models=… named anything, not only jev-*), workspace= and region=/plan= for a preset's plan; the editor's API seg has a fourth option, System One, whose Detect APIs posts a test question to <root>/systemone with the model typed, and a decide-only custom provider passes the "base URL is needed" check. A decide-only provider's first model is what it is asked as (Jev() no longer assumes jev-*), and its models stay routing groups' classifiers, never agents'. TestBailianDecisionPreset, TestCustomSystemOne, TestProviderSystemOne and TestProviderDecidePairs fail on the old code (undefined BailianDecision / DetectDecide, unknown decide=); internal/gui/tests/system-one.test.cjs (webkit, en/zh) covers the workspace, the Singapore and Token Plan plans, TypeSafe's unchanged editor and a custom System One detected and added. go vet, builds (darwin, GOOS=linux, GOOS=windows) and go test -tags nogui -count=1 ./... under a temp HOME pass but TestProvidersAnswerWhileListsComeIn, a timing test that passes alone. Not tried against a real Bailian key.

2026-10-03 15:21:15 +08:00

providers_unreadable_cli_test.go

provider: a providers.json that can't be read is said where the providers are listed, never backed up or synced as none, and is replaced through a rename (PR #415 's review) — #415 made edits refuse a file they couldn't read or decode, but every read for the user still took it as empty: magpie providers said "no providers yet", magpie models "no models yet", the Providers page opened the Add sheet as for a first use, and backup.Collect, so an export and a WebDAV/S3 sync, carried it as no providers, which another computer's Mirror would then take as every provider removed. magpie providers and magpie models now list what is left (the signed-in accounts) and end in the error, the TUI says it over its list, and the Providers page shows a "Your providers file can't be read" box (无法读取供应商配置文件) over the list with magpie's reason and no Add sheet; start-up, the gateway and the catalog still go on with it as empty. Stored and StoredGroups return the read error, so a backup and a sync stop on it with nothing pushed. The error, for reads and refused writes alike, names the file, says magpie left it unchanged and to fix it or move it aside (errors.Is ErrUnreadable). store writes through writePrivate, a 0600 temp file renamed over it (steady.Rename waits out a Windows reader holding it, a symlink keeps its target), instead of os.WriteFile's truncate-then-write, and the read goes through steady.ReadFile. TestFileErrorSaysUnreadable, TestWriteErrorsSayLeftUnchanged, TestStoredRefusesUnreadable, TestStoreReplacesAtomically, TestSyncStopsOnUnreadableProviders, TestProvidersCmdSaysUnreadable and provider-file-error.test.cjs fail without the change. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass; provider-file-error, click-scroll, old-webkit, providers-off-fold, add-sheet pass.

2026-10-01 19:45:24 +08:00

quota_cli.go

usage, gateway, gui, provider, cli: the tests pass when a run crosses midnight, and a usage answer reads the clock once (#1046 )

2026-10-07 02:14:29 +08:00

quota_history_cli_test.go

cleanup: gofmt the 15 Go files main had unformatted — whitespace, comment alignment and three one-line funcs gofmt opens up; nothing else. go build and vet -tags nogui pass.

2026-10-06 07:43:47 +08:00

quota_served_cli_test.go

tests: a fake that a test runs under a fixed wait is a file macOS has already let run, so the first-run check no longer kills it on a loaded Mac (WSL omp probe, Reasonix CLI, Grok install)

2026-10-07 07:08:16 +08:00

quota_wait_test.go

cli: magpie quota wait <provider|account> blocks until that subscription (any of its accounts) or that account has allowance again, then exits 0 (#720 , thedavidweng: a long Codex task stopped when every account ran out, and nobody came back to it hours later; step 1 of the maintainer's plan, for until codex exec …; do magpie quota wait codex || break; done) — it reads the vendors itself as magpie quota does, gateway running or not (provider.Allotted: the subscriptions' and plans' readings, no key balances; AskUsage has each look wait for a new reading, and only a wait for Claude runs Claude Code's /usage, through AskClaudeUsage, which now calls it). An account has allowance when routing's usedUp says so (no window that stops it, every model, at 100%; exported as provider.UsedUp), and BackAt is when the last of those windows starts again. While all are used up it sleeps to the soonest reset plus 30s, at least a minute and at most ten, saying on stderr what it waits for and until when; an allowance it can't read (an error, or only the last reading kept in its place) is asked again after 1, 2, 4, 8 then every 10 minutes. A provider's accounts switched off or signed out in magpie are left out, as the agent is never moved to them; an account is named by its user, or <provider>/<user> when two subscriptions share it. --timeout <duration> exits 1 when it passes first, --quiet says nothing, an unknown name or flag exits 2 (main now honours an exitError's code) and Ctrl+C 130. The loop takes its reading, clock and sleep as functions: quota_wait_test.go runs it on a fake clock (already available → no sleep; used up → 10m, 10m, then to just past the reset; one account named ignores another's room; a reset under a minute away is a minute; --timeout ends at the deadline after its last look; unreadable usage backs off and the wait goes on once read; an untold reset is looked at every 10 minutes; an off account is passed over; Ctrl+C), plus resolving names and the usage errors. Help in magpie quota's and magpie's usage, and the README. go vet, builds (darwin, GOOS=linux, GOOS=windows), the new tests and ./internal/provider pass; not run against real accounts.

2026-10-04 06:12:51 +08:00

quota_wait.go

provider, gateway: a usage window whose reset has passed is renewed on every path, and an account resting out of it is back once a reading finds it renewed (#1200 )

2026-10-08 06:24:44 +08:00

README.md

docs: README rewritten for what magpie does now — stat line, flow diagram, warm-up, context, image MCP, keep awake, agent updates, all 47 agents; "coding agent" is now just "agent"; per-agent notes moved to the reference

2026-10-08 16:36:33 +08:00

README.zh-CN.md

2026-10-08 16:36:33 +08:00

s3_cli_test.go

sync: moving between WebDAV and S3 keeps the other's server, and moving back finds it (ARNO on Discord: 我体验了一下s3同步，结果它把我之前配置好的webdav同步设置给删了) — sync.json held one setup, and saving S3 in Settings › Sync and backup (or magpie s3 on) wrote the bucket over it, so the WebDAV address, user and password were gone. sync.json now keeps the other kind's server beside the one synced to (other: its address, user, password or secret, and S3's endpoint, region and path-style), in the same file, readable by the user alone, and never in a backup, as before. Only one is synced to. Moving back with the password left empty uses the one kept, for the same server and user alone; magpie webdav on / magpie s3 on with nothing else given moves back to the kept one, and magpie webdav / s3 say which is kept. In Settings the row says "WebDAV settings kept" (or S3's), the form marks the kind synced to "· on", says whether saving keeps it or moves sync, its button reads "Move sync to WebDAV" when it does, and the other kind's fields show the kept server. A sync.json from before reads as it did; turning sync off still removes it all. TestConfigureKeepsTheOtherKind, TestS3Cmd and sync-other-kind.test.cjs fail without the change. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass; sync-other-kind, s3-sync, webdav-settings-refresh, click-scroll, old-webkit pass.

2026-10-01 19:44:29 +08:00

search_cli_test.go

2026-10-01 23:15:07 +08:00

search_cli.go

gateway: a model's web search goes to a search API of the user's own when no provider can search (#419 by HwFee: let me set up Tavily, Brave or SearXNG with my key rather than lose the search tool) — with no provider that searches by itself and no provider magpie could search with, the gateway took the client's web search tool away. Tavily, Brave Search, Exa, Firecrawl and SearXNG (an address of one's own, a key only if it asks for one) can now be set up, in an order: the injected web_search tool is then offered, and a search goes to the searcher's model as before, or, with none or when it fails, to each search API in turn, called directly with no model, its results handed back as the same hits and text the searcher path gives, so clients see the same web_search_tool_result blocks. The order is provider searches itself, searcher provider, search APIs, strip. They are kept in providers.json (0600) like provider keys; a backup carries them, their keys only when it carries keys, and one restored without keys keeps the key here; sync does the same, and a backup or sync from a magpie before them leaves the ones here alone. magpie search lists them, magpie search add <api> [key] [url=…] adds or updates one, magpie search rm <api> removes one; Settings has a Web search section (联网搜索) to add and remove them. Prompts, identity lines and headers to model providers are unchanged. TestWebSearchBySearchAPI, TestNoSearchAPINoTool, TestBackupSearchAPIs, TestSyncSearchAPIs and search-api.test.cjs fail without the change; TestSearchAPIsEachAsked checks each vendor against a fake, TestSearchCLI the command. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass; search-api, provider-search, click-scroll, old-webkit pass.

2026-10-01 19:44:44 +08:00

serve_cli_test.go

gateway: advertise MAGPIE_PUBLIC_URL in the console and CLIs (#373 )

2026-10-02 00:46:45 +08:00

sessions_cli_test.go

tests: a test that sets time.Local does it through testenv.Zone, which first waits out the stand-ins' first runs — their os.Stat reads time.Local, and TestDsh -race alone raced it every run

2026-10-07 06:17:56 +08:00

sessions_cli.go

sessions, gui, tui, cli: the Sessions list is as long as the count beside it, and drawn in pages (#1019 )

2026-10-07 00:16:13 +08:00

signals_test.go

fix(proc): end what a CLI probe started, on its timeout and when magpie exits (#414 )

2026-10-02 00:42:48 +08:00

signals_unix.go

fix(proc): end what a CLI probe started, on its timeout and when magpie exits (#414 )

2026-10-02 00:42:48 +08:00

signals_windows.go

fix(proc): end what a CLI probe started, on its timeout and when magpie exits (#414 )

2026-10-02 00:42:48 +08:00

signals.go

fix(proc): end what a CLI probe started, on its timeout and when magpie exits (#414 )

2026-10-02 00:42:48 +08:00

update_auto_cli_test.go

settings: save atomically and preserve unreadable configuration (#621 )

2026-10-03 11:21:04 +08:00

update_cli.go

update: install.sh and magpie update take --proxy and --mirror, and magpie update mirror keeps one for the app's updates too (akic404 on Discord: 安装和update如果没有梯子也是麻烦事，能否在install.sh和magpie update后加子选项？--proxy等可自定义或默认ghproxy) — install.sh had no options and fetched with curl alone, and magpie update took none; without a way out to GitHub both failed. Now both take --proxy <url> (http, https, socks5, socks5h; install.sh also MAGPIE_PROXY=) for the feed and the download, and --mirror <prefix> (or MAGPIE_MIRROR=), a GitHub download mirror the release file is fetched from as <prefix>https://github.com/…; only github.com / githubusercontent.com URLs are put through it. No mirror is used unless one is given: magpie names none and has none by default. The feed with each file's SHA-256 is always fetched from usemagpie.ai, never through the mirror, so a file the mirror changed is refused and deleted ("… from the mirror X does not match its checksum from https://usemagpie.ai ; not installed"); macOS still checks the app's signing team. magpie update mirror <prefix>|off saves Settings' updateMirror (http(s) only), which the app's own background update follows too; magpie update --mirror off skips it once; the Settings page's save keeps it. The app's update already followed Settings → Proxy (#294 ); magpie update --proxy overrides it for one run. The environment's ALL_PROXY / all_proxy is now honoured when HTTPS_PROXY / HTTP_PROXY are unset (Go's ProxyFromEnvironment ignores it), with NO_PROXY as curl reads it. magpie update takes --flag value or --flag=value, and an unknown word is an error instead of an update. The help, README and the docs' FAQ (en/zh/ja) say how. install.test.mjs's proxy, mirror and tampered-mirror tests, TestAllProxyFromTheEnvironment, TestUpdateThroughAMirror, TestUpdateThroughAProxyGiven and TestUpdateFlags fail on the old code and pass; TestSettingsSaveKeepsWhatItDoesNotSend covers updateMirror. A dry run of install.sh as Linux amd64 into a temp HOME installed the real 0.1.773 with its SHA-256 checked, refused a local mirror serving a wrong file, and with --proxy to a closed port failed reaching the site through it. go vet, builds (darwin, GOOS=linux, GOOS=windows), sh -n, node --test site/install.test.mjs and go test -tags nogui -count=1 ./... under a temp HOME pass but TestClaudeIdentityServedWhileAsked, a timing test that passes alone. Not tried through a real proxy server or a real public mirror; no install.ps1 exists for Windows, and the app has no field for the mirror.

2026-10-04 00:19:47 +08:00

update_flags_test.go

2026-10-04 00:19:47 +08:00

usage_cli_test.go

usage, gateway, gui, provider, cli: the tests pass when a run crosses midnight, and a usage answer reads the clock once (#1046 )

2026-10-07 02:14:29 +08:00

usage_cli.go

usage, gateway, gui, provider, cli: the tests pass when a run crosses midnight, and a usage answer reads the clock once (#1046 )

2026-10-07 02:14:29 +08:00

visible_cli.go

models: each agent can be shown only some of them — a provider or group gets a family (magpie provider set relay-x family=relay), and magpie visible zcode relay shows zcode only that family's models (or named providers and groups): in the files magpie writes for it and in what /v1/models answers it, told apart by its User-Agent; magpie models zcode lists what it is shown and what is kept from it, and magpie visible zcode all shows it everything again. A model kept from an agent is still served when asked for by name. Asked for on Discord

2026-09-26 16:02:29 +08:00

web_cli.go

gui, web: gateway mode — magpie web on a server that is only a gateway shows no Agents, Sessions or Library (Player on Discord) — a magpie web run on a server or NAS for other machines' agents showed the Agents, Sessions and Library pages and the settings written into this machine's agents, none of which do anything there. In gateway mode the page has Providers, Gateway, Routing, Usage, Plugins and Settings; an address kept for a page left out opens Providers. Settings leaves out provider in model names, Codex subagents, long conversations, Codex thread titles, the usage/balance alerts and reset reminders, on top of the tray, open at login, Dock, text size and lightweight rows magpie web already hid; Language, theme, currency, proxy, redaction, vision/image models, sync, updates and the rest stay. magpie web is in it by itself when it finds no agents on its machine (the Docker image, a NAS) and with the new magpie web --gateway; Settings › General › Gateway mode (Automatic / On / Off, saying why it is on) wins over both and Off brings every page back at once. The choice is this machine's own (KeepOwn: never synced or restored from another computer), set only by POST /api/settings/gateway-mode, never by the Settings page's save. The app's own windows are never in gateway mode. boot.js tells the page before it paints. en/zh/ja/de; docs/reference.md (Docker › NAS, CLI list). TestGatewayMode (temp HOME: no agents → on, agents → off, --gateway → on, Off wins over --gateway, the Settings save leaves it, On with agents, Automatic, an unknown mode refused, the app window never told, KeepOwn) is new; TestSettingsSaveKeepsWhatItDoesNotSend sets it. gateway-mode.test.cjs (WebKit, en and zh: the tabs, ?view=agents/sessions/library open Providers, the switch and why, the seven rows hidden, Off posts "off" and brings tabs and rows back with Settings kept open and Agents opening, Automatic hides them again, the Settings save never sends it, no scroll, no select, no left border; web with agents and the app window keep every tab, the switch is magpie web's alone) fails without the change. mobile-web's desktop comparison differs from origin/main on Settings only, by the new row. settings-sections, settings-groups, click-scroll, cli-path, plain-names, codex-titles and agent-grip pass in WebKit. go vet, go build (darwin, GOOS=linux nogui, GOOS=windows) and go test -tags nogui ./... under a temp HOME pass.

2026-10-05 18:20:28 +08:00

webdav_cli_test.go

test: one list of the agent folders a sandbox clears, so no sandbox misses an agent (yetone, on #522 : A shared list of env vars for the other sandboxes would be a welcome follow-up) — every sandbox kept its own list of the variables that point at an agent's folder, and each had drifted: the gateway's cleared 5 of the 32 magpie reads, the provider package's 2, the tui's 10, the library's 20. A sandbox clearing 2 meets whatever Grok, Kimi, Hermes, MiniMax, Qoder or ZCode the developer has installed, which is how #522 came about — Qoder's two were in the library's list and in none of the four that failed. internal/agentenv is now the one list, and the 21 sandboxes that fake an environment with no agent in it clear it, each keeping beside it the variables that are not an agent's: APPDATA and LOCALAPPDATA, which a sandbox sets to a folder of its own rather than clearing, VISUAL and EDITOR. A name in the list is one magpie reads, and TestVarsAreRead walks the sources to say so, which is how two names a sandbox had been clearing turned out to be read by nothing at all — GEMINI_CLI_HOME and OPENCODE_CONFIG in internal/backup's, while OPENCODE_CONFIG_DIR, the one internal/agent reads (agents.go:545), was not in it. Where a sandbox set an agent's folder to a fixture of its own, the clearing now comes first, since a list of 32 wipes what a list of 5 left standing. Not converted: the omp tests' four variables, which are the ones omp's own lookup consults (a Pi fork) rather than every agent's, and the warm-up's Claude Code traffic flags, which are not folders — CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC stays out of the list for that reason too, its one test setting it on purpose. On Windows 11 the whole suite answers as it did before the change: 31 packages pass, and the same 15 tests in internal/library, internal/gateway and internal/agent fail for what they failed for before (symlinks this machine has no privilege for, and TestSuffixModesReachAgentFiles). go vet ./..., go build -tags nogui (windows, GOOS=linux, GOOS=darwin), and go vet -tags nogui for linux and darwin over every package touched pass. (#543 )

2026-10-02 17:22:16 +08:00

webdav_cli.go

sync: it can sync by itself less often or only when asked, and the server's setup can be restored over this computer's, undoably (Sun1090, #847 : 同步太快了，需要设置个开关控制自动同步，还有恢复按钮) — the gateway's magpie synced every 3 minutes with no way to change it, and a free 坚果云 account is allowed only so many WebDAV requests (600 per 30 minutes, 1 GB up and 3 GB down a month); and there was no way to take the server's setup back over a computer's own, which the next sync would otherwise push up. Settings › Sync now has Sync by itself, the app's segmented control (no <select>): Off, 3 min (the default, as before), 15 min, 30 min, 1 hour; Off syncs only on Sync now, and the sync row says only when asked. The loop reads the setting each minute (no request), so a change takes effect without a restart, and a server limiting requests is still waited for as backoff says. Restore from the server asks first in the app's own dialog, naming the parts replaced; it reads the server's file as it is now, seals this computer's setup (keys and all) into the sync folder as <time>-before-restore (newest 5 kept), brings in each part that differs as a sync brings one changed only there, and leaves the state as such a sync would, so the next sync pushes nothing back. Its notice says what was restored, with Undo, which brings the kept setup back (the next sync then takes it to the others); OK, or a later sync's own notice, drops the undo. The form's Save keeps the setting (SetAuto alone sets it). CLI: magpie webdav|s3 auto off|3|15|30|60, restore, undo; the status says how often it syncs by itself. zh, ja, de strings. TestAutoSync (off: no request by itself; back to 15 min: one sync, then none; Save keeps it; 7 refused) and TestRestore (b's own changes replaced by the server's with no push, the kept copy holds b's provider and key, Undo puts it back and a gets it, nothing differing restores nothing) pass -race; sync-auto-restore.test.cjs (WebKit, en and zh: Off posts -1 and the rows say so, Cancel posts nothing, Restore and Undo post, no click moves the page) fails on the old code. sync-other-kind, sync-spin, s3-sync, webdav-settings-refresh, usage-computers, click-scroll, gui-ja, gui-de and settings-sections pass on WebKit. go vet, builds (darwin, GOOS=linux nogui, GOOS=windows) and go test -tags nogui -count=1 ./... under a temp HOME pass.

2026-10-05 10:36:46 +08:00

README.md

magpie

Every agent's model. One place.

Claude Code on Kimi. Codex on DeepSeek. Gemini CLI on GLM. OpenCode on your ChatGPT plan.
Switch any of them from the menu bar. One local gateway serves them all,
and when a quota runs out, it quietly moves on to the next account.

Download · Docs · Reference · Plugins · Discord · English · 简体中文

magpie's Agents page: Claude Code on Kimi K3, Codex on DeepSeek V4 Pro, Gemini CLI on GLM-5.3, each picked from one list

45+

agents, one list

4

wire APIs, one gateway

5

routing modes

0

config files edited by hand

Why magpie

You probably use more than one agent. Each keeps its model in its own file, in its own format, with its own keys and base URLs, and its own opinion about which vendors it supports. The subscription you pay for works in one agent and nowhere else. And when it runs dry at 3 pm, you're back to editing config files.

magpie gathers all of it into one place.

🎛 One screen

Every agent on your machine, in one list. Click a model, pick another. magpie changes exactly one key in the agent's own config. Comments, order and formatting stay untouched.

🔌 One gateway

127.0.0.1:3425 speaks OpenAI Chat, OpenAI Responses, Anthropic Messages and Gemini, and translates between them. Streaming, tool calls and reasoning included.

🔀 Routing that keeps going

Group models from several providers. When one is rate-limited or out of quota, the next one answers. Your agent never sees the error.

🔑 Subscriptions, shared

Your Claude, ChatGPT, Copilot, Gemini or Grok sign-in becomes a provider that every other agent can use. No key to copy.

🧩 Plugins

OpenCode auth plugins and pi packages from npm run inside magpie. A plugin can also be gateway middleware that rewrites every request and reply.

📊 Every token, counted

Tokens, cache hits, cost at list price, balances and quota windows for every provider, account and session, with limits per key.

How it fits together

flowchart LR
  subgraph A["Your agents"]
    direction TB
    a1["Claude Code"]
    a2["Codex"]
    a3["Gemini CLI"]
    a4["OpenCode · Zed · Cursor CLI · 40+ more"]
  end
  subgraph M["magpie · 127.0.0.1:3425"]
    direction TB
    g["Gateway<br/>Chat · Responses · Messages · Gemini"]
    r["Routing groups<br/>fail-over · smart · pace"]
    p["Plugins & middleware"]
    g --> r --> p
  end
  subgraph P["Your providers"]
    direction TB
    p1["API keys<br/>DeepSeek · Kimi · GLM · OpenRouter …"]
    p2["Subscriptions<br/>Claude · ChatGPT · Copilot · Gemini · Grok"]
    p3["Local models<br/>Ollama · LM Studio"]
  end
  A --> M --> P

Any model, any agent

Click a value and a searchable list opens: every model of every provider you added, as provider/model. Pick one and the agent's config is rewritten safely and atomically. Start a new session and the agent is on the new model.

Profiles save the setup of every agent under one name ("Budget", "Focus") and switch them all back in one move. Each agent can also have its own short list of models, so its picker shows only what you want there.

magpie lives where you are: a menu bar panel on macOS, Windows and Linux, a full window, a TUI (magpie tui), a web UI (magpie web, for WSL or a server over SSH) and a plain CLI.

A provider is one field away

Pick a preset, paste a key, done. Model lists come straight from the vendor, with names and reasoning levels filled in from models.dev, so a model released this morning is in your picker on the next refresh. Nothing is compiled in.

Presets include Anthropic · OpenAI · Google Gemini · DeepSeek · Kimi · Zhipu GLM · MiniMax · StepFun · Qwen · Baidu Qianfan · Tencent Cloud · Huawei Cloud MaaS · Volcengine Ark · Mistral · Groq · xAI · OpenRouter · Together · Fireworks · SiliconFlow · NVIDIA NIM · ModelScope · Ollama · LM Studio … and any OpenAI- or Anthropic-compatible URL.

Add provider: subscriptions to sign in to, vendors, relays and local servers

Already set up elsewhere? Import brings in the providers from CC Switch, Claude Code, Codex and Alma. Add to magpie links let a provider's website hand its config to magpie in one click. Each key, like each account, can go through a proxy of its own.

Routing that keeps going

A routing group is several models an agent picks as one, such as group/daily-coding. The gateway spreads requests over every member's keys and accounts:

Mode	What it does
`smart`	Of the subscriptions with quota left, use the one that renews soonest, so less is wasted at the reset
`order`	Use the first model until it can't answer, then the next
`rotate`	Move to the next member on each turn
`usage`	Use the least-used member first
`pace`	Use the account with the most of its week left per hour until it resets

Conversations stay with the account that answered them while the vendor's prompt cache is still worth keeping. Intent routing goes further: a small model of your choice reads each new turn, so tests go to the strong model and quick questions to the fast, cheap one. Groups can contain groups, and the Routing view shows every decision live.

The Routing view: four agents through magpie to seven providers, live

An intent-routed turn, explained step by step

→ Intent routing, in depth

An agent you're signed in to is a subscription with models behind it, so magpie offers it as a provider. Add several accounts per subscription and magpie fails over between them.

Claude: drives the real local claude binary and bridges your agent's tools over MCP
Codex / ChatGPT: your ChatGPT plan's models, in every other agent
GitHub Copilot, Gemini (Code Assist), Antigravity, Grok (SuperGrok) and more
Any OpenCode auth plugin or pi package from npm

Daily warm-up starts each Claude and ChatGPT account's 5-hour window at the times of day you choose, or the moment the last one resets, so your windows line up with your day instead of with your first prompt.

Plugins

magpie plugin add opencode-gemini-auth   # an OpenCode plugin from npm
magpie plugin add pi-antigravity         # a pi package, the same way
magpie plugin login google-plugin        # its own sign-in flow, in magpie

magpie runs plugins on Bun, downloaded the first time a plugin needs it. A plugin signs in, lists its models and makes each request; agents use those models like any other provider's. Browse magpie-community/plugins, or write your own.

A plugin can also be gateway middleware: JavaScript that sees what every agent sends and gets back, whatever the provider. onRequest can rewrite a request or turn it away, onEvent sees each streamed event, onResponse sees the whole reply. It runs in-process, about a microsecond per event, and a hook that throws or runs too long leaves the request as it was.

// alias.middleware.js — magpie plugin add ./alias.middleware.js
export function onRequest(body, ctx) {
  if (body.model === "fast") return { ...body, model: "deepseek/deepseek-chat" };
}

Ready-made middleware, most of it what New API does for its channels, with the same JSON

Package	What it does
`param-override`	New API's `param_override`: set, delete, move or rewrite request fields, under conditions, or turn a request away
`model-map`	New API's `model_mapping`: send a model under another name; replies keep the name asked for
`system-prompt`	Your system prompt on every request, or some agents' or models'
`word-guard`	New API's sensitive-word filter: turn away or mask words in what users send, and in replies
`think-tags`	Take `<think>…</think>` out of replies, or put `reasoning_content` into them

magpie plugin add @magpie-community/middleware-model-map
magpie plugin options model-map '{"mapping": {"fast": "deepseek/deepseek-chat"}}'

Find them under Plugins › Discover › Gateway middleware. See Gateway middleware.

Every token, counted

The Usage page: balances, tokens, cache hit rate and cost

Tokens, cache reads and writes, reasoning and calls, with cost at list price, in dollars or yuan. Set your own price for any model.
Balances and quota windows for every key, plan and subscription account (magpie quota). A reset reminder warns you before a window renews with much of it unused.
Sessions: every agent conversation with its cost and title, reopened in your terminal with one click.
Context: how full each request's context window is, how much came from the cache, and what fills it, part by part.
By account and by upstream key, so you can check a vendor's bill line by line, and OTLP export to your own observability stack.

On your network. Turn on Share on local network and give each client a named gateway key, each with its own daily, weekly or monthly token and cost limit.
Remote magpie. A laptop can use the providers, accounts and routing groups of the magpie on your desktop, while still wiring its own agents.
Docker. Run ghcr.io/yetone/magpie on a server or a NAS and manage it from the web UI.
Sync. Back up to a file, or keep machines in sync over WebDAV (Nutstore, Nextcloud…) or S3.

The little things

📚 Library. Write instructions, MCP servers and skills once; magpie writes them into each agent's files in that agent's format, and removes only what it wrote.

🖼 Images and video. Give any agent an image tool through MCP, made with the model you choose, and videos with a Grok subscription.

☕ Keep awake. Your computer doesn't go to sleep in the middle of an agent's task.

⬆️ Install and update agents. The Agents page shows each CLI's version, updates it the way it was installed, and gives the commands to install the ones you don't have yet.

🐧 WSL. On Windows, agents inside WSL distros are wired too, and their sessions counted.

🎨 At home on your desktop. Light and dark, and on Omarchy magpie takes your theme's look.

Supported agents

Claude Code · Claude Desktop · Codex · Gemini CLI · Antigravity CLI · OpenCode · OpenChamber · MiMo Code · Pi · oh-my-pi · Aside · OmO · Goose · Cursor CLI · Cursor Private Inference · Zed · VS Code Chat · VS Code Insiders · VSCodium Chat · JetBrains Air · Copilot CLI · Crush · DeepSeek Harness · Reasonix Studio · Command Code · fx · Devin · Hermes Agent · Mister Morph · Kimi Code · Muse Code · Empryo · MiniMax Code · Droid · Cline · Qoder · Qoder CN · Grok Build · ZCode · WorkBuddy · CodeBuddy Code · Pencil · T3 Code · OpenHanako · AtomCode · Alma · Cindy

magpie shows only the agents installed on your machine; setup notes for some of them are in the reference. Anything else that takes a base URL can use the gateway too:

export OPENAI_BASE_URL=http://127.0.0.1:3425/v1     OPENAI_API_KEY=magpie
export ANTHROPIC_BASE_URL=http://127.0.0.1:3425     ANTHROPIC_API_KEY=magpie
export GOOGLE_GEMINI_BASE_URL=http://127.0.0.1:3425 GEMINI_API_KEY=magpie

Quick start

1 · Install. Download the app from usemagpie.ai, or run:

curl -fsSL https://usemagpie.ai/install.sh | sh

_{Mac builds are signed and notarised, and every build updates itself. Behind a firewall, use --proxy or --mirror. Or go install github.com/yetone/magpie@latest, or the Docker image.}

2 · Add a provider. Open magpie and go to Providers → Add provider. Pick a preset, or sign in with a subscription.

3 · Pick a model for each agent on the Agents page. Start a new session and it's on the new model.

Or do it all from the terminal:

magpie provider add deepseek sk-…              # a preset needs only the key
magpie claude deepseek/deepseek-v4-pro          # Claude Code on DeepSeek
magpie codex moonshot/kimi-k2.5                 # Codex on Kimi
magpie group add "Opus anywhere" models=claude/claude-opus-5-5,copilot/claude-opus-5.5 routing=smart
magpie claude group/opus-anywhere               # fails over between subscriptions
magpie save work && magpie use work             # profiles
magpie quota                                    # what's left on every plan
magpie tui                                      # the whole thing, in a terminal

Documentation


Get started	The guided tour
Reference	Every agent, provider option, gateway endpoint, CLI command and file
Plugins	Use plugins and write your own
Intent routing	Route each turn by what it asks for
Import links	"Add to magpie" buttons for provider websites

Community

Questions, ideas, or a model that won't show up? Join us on Discord or open an issue.

If magpie saved you from editing one more config file, a ⭐ helps others find it.

License

MIT

README.md Unescape Escape

magpie

Every agent's model. One place.

45+

4

5

0

Why magpie

🎛 One screen

🔌 One gateway

🔀 Routing that keeps going

🔑 Subscriptions, shared

🧩 Plugins

📊 Every token, counted

How it fits together

Any model, any agent

A provider is one field away

Routing that keeps going

Sign in once, use it everywhere

Plugins

Every token, counted

Share one magpie

The little things

Supported agents

Quick start

Documentation

Community

License

README.md