A developer of an AI app asked how to work with magpie and whether an app can
register itself after one confirmation. The page says what exists: the
gateway (find it via /api/hello and settings.json's port, the OpenAI,
Anthropic, Responses and Gemini endpoints, /v1/models' fields), how a key
magpie-<id> or the User-Agent's first word names the app in Usage, a row on
the Agents page by an adapter PR in internal/agent (config-edit, Cindy-style
own import link confirmed in the app, or a local API) with what the PR needs,
what plugins can and can't do, and what isn't there: no link or API registers
an app or installs a plugin, and magpie://import adds providers only. English
and Chinese pages, linked from every docs page's nav and footer.
TestThirdPartyAppIsCountedAsItself pins the attribution the page promises.
go vet and the gateway tests pass; site node tests pass; pages checked in
headless Chromium (no errors, TOC, no horizontal scroll at 390px).
* agent: AtomCode is wired like its own CodingPlan sign-in — one provider account, one model table per catalog model
AtomCode (atomgit.com/atomgit_atomcode/atomcode, AtomGit's open Rust terminal agent) keeps its settings in ~/.atomcode/config.toml ($ATOMCODE_HOME). Its account schema, what its own CodingPlan sign-in writes, is one [provider_accounts."magpie"] table at the gateway's /v1 (protocol openai, gateway.TokenFor("atomcode") as the key, so a request is its agent's even when the UA is overridden) and one [models."magpie/<provider>/<model>"] table per catalog model: the model string goes to the gateway as it is to resolve, with the model's context window (AtomCode compacts as it nears it; a 128000 one is told when the model's isn't known, and an output above the told window is cut to it), its output limit, vision and reasoning_effort_levels; reasoning_effort rides on the table once the user picks one. Picking a model points default_provider and default_model at it — default_model wins when both are set, as atomcode reads it — and stashes the defaults the user had; stepping out puts them back. The picker offers the user's own model tables and the catalog via magpie; the Library gives AtomCode its ATOMCODE.md, its mcp.json (omp's shape) and skills/; its UA is atomcode/<version>.
Found against a real atomcode 5.2.1: the documented legacy [providers.*] tables work, but its own sign-in writes the account schema, so magpie writes that; reasoning_effort, max_tokens and supports_vision were verified to reach the request from the model table, and default_model to win over default_provider. Verified end to end on a real install: atomcode --provider "magpie/…" answered through the gateway, and the Agents page shows the tile, its picker and the Usage attribution. TestAtomcodeWiring, TestAtomcodeRestoresOwnDefaults and TestAtomcodeSync fail on the old code; TestDriftUnwiredEveryAgent and TestUnsetAgentsReadEmpty cover it from All(). go vet, builds (darwin, GOOS=linux, GOOS=windows) and go test -tags nogui -count=1 ./internal/agent ./internal/library ./internal/agentenv pass; the plugin-host and timing failures of the full ./... run fail on main without this change too.
* tweak
* agent: AtomCode's config is matched by its own spellings, and Sync keeps the effort — AtomCode rewrites its config through serde on every /model and /cd, and that writes the account header bare ([provider_accounts.magpie]) where magpie wrote it quoted, so after the first rewrite Check read the wiring as gone, Sync and every pick appended a second account table (edited TOML is invalid: table magpie already exists) and clearing left the unquoted table and its api_key behind. The account is now matched by exact name in its three spellings (quoted, bare, literal — magpie-2 stays out) and the model tables by their decoded keys (kimiModelKey, replacing atomcodeModelName), through a new SetTOMLTablesMatching that takes exact names beside prefixes; SetTOMLTables delegates with none, unchanged. Sync carries each magpie model table's reasoning_effort over when rewriting — it ran at every gateway start and catalog change and dropped both an effort picked in magpie and one picked with AtomCode's /effort, and picking another model cleared every table's. The effort Set validates against the levels AtomCode knows (low, medium, high, xhigh, max — its clamp_effort_to_levels drops none, minimal and ultra), a model without levels offers none now, and the low/medium/high fallback is gone with it. supports_vision is written explicitly false, where AtomCode otherwise guesses from the model name. The user's legacy [providers.*] entries join the picker, a stashed default_model naming one comes back on Disconnect, and picking one sets default_provider and takes default_model out, as the legacy shape reads. site docs (en, zh, ja) list AtomCode. TestAtomcodeSync rewrites the config into the bare and single-quoted spellings before Sync and again before clearing and fails on the old code (drift reported, effort dropped, unquoted table left behind); TestAtomcodeLegacyProvidersArePickableAndRestored and TestAtomcodeEffortLevelsMatchAgentSupport are new. Reported by yetone on #736. go vet, builds (darwin, GOOS=linux, GOOS=windows) and go test -tags nogui -count=1 ./internal/agent ./internal/edit pass.
* agent: TestAtomcodeWiring picks an effort through the field too — the write side of the validation the last commit added (a level AtomCode knows lands as reasoning_effort on the model table, one it does not know is refused) had no coverage left: the test only read back what AtomCode's own /effort had written. provider.SetModelEfforts gives fake/m1 levels to offer.
* agent: Disconnect puts AtomCode's default_provider back only where AtomCode still has it — the restore checked the stash's value was not magpie's but not that the table it names was still there, so a table the user had deleted in between came back as a dangling default (the account schema's default_provider names a model table, the legacy shape a [providers.*] one; own answers for both). The default_model branch checked already. TestAtomcodeRestoresOwnDefaults deletes the stashed provider's model table before clearing and fails on the old code.
* agent: AtomCode joins the CLI updates — npm @atomgit.com/atomcode, the brew cask atomcode, and the curl script's ~/.local/bin/atomcode updating itself with atomcode upgrade, so the Agents page shows its version and a newer one as the other agents' do (#736). TestHowInstalled covers the npm prefix, the cask and the self-updating installer.
* agent: AtomCode's self-updater waits for its install paths to be confirmed — the branch recognized a binary under ~/.local/bin as `atomcode upgrade`, on a docs page, while the README shows another path and the command has not been driven outside the help text; the reviewer asked for it removed until the standalone command and the script's real default are settled. npm and the brew cask stay, with their tests; a comment marks what is pending.
---------
Co-authored-by: googya <118465+googya@users.noreply.github.com>
* routing: Least used puts first the account with the most of its week left per hour until it renews — it ranked by the share used alone, so with two subscriptions, one 80% through its week and renewing in an hour, the other fresh and renewing in five days, every new conversation went to the fresh one and the first's remaining 20% was lost at its reset. Allowance.Pace: over the windows that count the model and run a day or longer (the five hours are a rate cap, not a budget; Kiro's month counts), (100 − used) / hours to reset — a week not started or not known runs its whole span from now, one whose reset has passed is full again, of several (Opus's own beside the general) the tightest; an account whose vendor tells the five hours alone (Claude's own usage command) counts as a week not started with their share used, so those go by what they have used, as they did. weigh's LeastUsed case: one at 98% or more last whatever its week, by how far; then pace, highest first, in bands alike within a tenth drawn from the top before sorting (a pairwise tenth isn't an order: three paces a twelfth apart go round in a circle); within a band the tokens sent lately, then their order, for the cache; an account not known counts as a fresh week (before, "used 0" put it first), a key follows the subscriptions. Renewing the same hour, pace is most-left-first, as before. Smart untouched. The trace carries pace; the Routing tab's story, the provider and group editors' hints and the docs' routing table (en, zh) say what the option goes by now. TestAllowancePace, TestLeastUsedPace (fails on the old weigh: "imminent renewal first: ab"). go vet ./internal/..., go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./internal/provider/ ./internal/gui/ pass; ./internal/gateway/ passes but TestPluginModelListThroughAccountProxy, which fails on main too (a concurrent Body.Read panic in its fixture).
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* routing: weekly pace is its own option, "pace"; Least used keeps its meaning (yetone, #517 review) — a user who had picked Least used was being switched to another strategy under the same name. Weekly pace: the account with the most of its week left per hour until it renews goes first, the one with the most to lose at its reset; Least used is most-left-first again, Smart untouched; the CLI takes routing=pace (weekly-pace), the TUI cycles to it, the group and provider editors, the Routing tab, README and the docs' routing tables (en, zh) list it. Review points: the tiers are Smart's — one at 90% or more of any window that counts the model, the five hours too, waits behind the healthy ones, by share, one all but used up behind those (an account 95% through its five hours with a healthy week ranked ahead of a fresh one until 98%, and the allowance is read about once a minute, so it was sent into 429s); among the healthy, one not known that tells what it has left as it answers (a Claude account) goes first while it isn't known, as in Smart, else it would never answer and never be known; a window that says no span (a plugin may not) is a budget for as long as its reset says, else a week, where it fell among the five hours and made the week not started; the hours until a reset are never fewer than one, or a window thirty seconds from renewing paced at 6000; the trace carries due, the reset of the window the pace went by, and the Routing tab's story says the week's share left over the hours until that, not the first reset it finds; Routing's comment in provider.go and README's routing= line name the option. The bands of pace alike are drawn among the healthy known accounts alone: one running low would otherwise set a band's top and part two alike behind it. TestWeeklyPace (the tiers and their 90% edge, the probe and its end, the bands drawn without the low, keys by tokens and after subscriptions, the trace's pace and due, Least used unchanged), TestAllowancePace (due, the span-less budget at 48 h and at 90 min, a day the shortest budget, the hour floor, normalize keeps pace). go vet ./internal/... ., go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./internal/provider/ ./internal/gui/ ./internal/tui/ . pass, the two new tests 25 times over; ./internal/gateway/ passes but TestPluginModelListThroughAccountProxy, which fails on main too.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
---------
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
* agent: MiMo Code — a terminal coding assistant that is Xiaomi's fork of OpenCode, whose config keeps OpenCode's shape: its own mimocode.json(c) under ~/.config/mimocode, its auth beside it, and a magpie provider block with npm/@ai-sdk/openai-compatible, model and small_model fields. opencode() becomes openCodeLike() for the two to share it, and magpieProviderJSON splits shape from the catalog id (magpieProviderJSONFor), so a visibility narrowed on mimocode (magpie visible mimocode …) narrows its list and leaves OpenCode's alone. The library gives it the same instructions, MCP servers (its mcp key) and skills as OpenCode, except the shared skills go into its own skills/ folder: it reads Claude Code's skills only behind a flag, though it reads its CLAUDE.md like OpenCode, and the page says so. Its requests are told by the mimocode/ User-Agent. Checked against XiaomiMiMo/MiMo-Code
* icon: MiMo Code's own favicon, from packages/ui/src/assets/favicon — its frame with the bottom bar, in the monochrome the app masks to the text colour
yetone