efd501ec749834f70db46be2497f20e2eaf7472e
46
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 TryWorldandh4rK8s
|
efd501ec74 |
agent: add Reasonix Studio with separate Executor and Plan models (#427)
* feat(agent): add Reasonix Studio 2.x integration
* agent: select Reasonix planner independently from executor
* agent: restore Reasonix when its credential file was initially absent
* agent: preserve Reasonix planner choices and model controls
Keep configured and saved native planner references selectable, and retain full model picker behavior and role labels. Exercise native planner restoration and both browser layouts. Separate temporary CLI first-launch work from version and intentional timeout assertions.
* test(gui): follow the current Reasonix connection flow
* test(gui): open connected Reasonix details before checking roles
* agentenv: isolate Reasonix configuration in test sandboxes
* gui: restore Reasonix roles without disconnecting the other
* gui: Reasonix's role labels read in every language, and its confirm names them
The review found four things on the Reasonix roles' strings.
"executor" and "planner" are field labels like any other, so t() translates
them; they had no i18n entry in any language, so the zh, ja and de windows
showed the English key. They now read 执行模型/规划模型, 実行モデル/計画モデル
and Executor-Modell/Planner-Modell, beside model/effort/thinking in each block.
The confirm said "neither Executor nor Plan" — names that appear nowhere in
the UI — and its zh text said "Executor 和 Plan", while the fields are labelled
executor and planner. It now names the labels, and each language names its own
translation of them (zh 执行模型和规划模型, ja 実行モデルも計画モデル, de vom
Executor- bzw. Planner-Modell).
Both new strings had a zh entry and no ja or de entry, which is what turned
gui-ja and gui-de red: every zh key needs its ja and de with the same
placeholders. "restore the previous {field} selection" also started at column
0 in i18n.js; it is indented with the lines around it now.
reasonix-roles.test.cjs asserts the rendered label, so its zh expectations name
执行模型/规划模型; the en ones stay as they were, the en label being the key.
Its en assertions on the confirm's first sentence are unchanged, and the
reworded second sentence is not asserted.
Verified on this head: gui-ja passes 3/3 and gui-de 3/3 (every zh string has
its ja and de, same placeholders and tags); reasonix-roles.test.cjs passes 8/8
in Chromium and WebKit, en and zh, window (1000px) and panel (440px); go vet
./... and the four builds pass. The rest of internal/gui/tests was run and
compared against a clean main worktree at
|
||
|
forever
|
f109b270c0 |
gui: the main window opens as it was last left — maximised again if it was, at its last size otherwise (#995)
On a MacBook the window had last been zoomed. magpie skipped a maximised window when it saved the size, so it reopened at an older, nearly full size: 1712×1083 at (8,34) on a 1728×1084 work area, neither full nor the size it was given nor the default. settings.WindowMaximised (this computer's own, KeepOwn) now records whether the window was maximised when it settled; Window stays the size it restores to (settle). A window not shown yet, let go, full screen or minimised, or on Linux hidden, records nothing. Reopened maximised: on the Mac and Windows placeMain maximises the made window just before its first Show (on Windows once its page has come); Wails' StartState is undone by the Mac's centring and shows a Windows window before its page. The least size Maximise drops is put back. On Linux makeMain sets StartState, since GTK can't be asked about a window not mapped yet. A size kept on a larger screen: Windows fits the window to the work area and centres it, title bar in reach, and keeps the larger size for the larger screen (fitted); the Mac fits and zooms it itself, and magpie doesn't zoom it again, so it can still be restored. TestSettle fails with upstream's rule (5 of 9 cases); TestOpenSize, TestFitRoom, TestWindowMaximisedKeptAndOwn; the Mac's real build under a sandbox HOME, 11 cases. |
||
|
forever
|
8754221203 |
gateway, usage: when the credits switch holds every account, the record and 429 say so accurately; the switch's text says it follows the latest reading (#999)
* gateway: a request refused as every account is held records why, caps or credits When every account was held, the request's record always read "every account at its usage cap", though the client's 429 (cappedError) already told a usage cap, credits set not to be spent, and the two together apart. The record now comes from the same classification (heldBy): the cap-only wording is kept, credits-only reads "every account held: set not to spend its credits", and a mix names both. TestCodexNoCreditsEveryAccount checks the record for both requests; with the old fixed string it fails with: recorded 429 "every account at its usage cap" (twice). Follow-up to #974. * gateway: the 429 for accounts held off their credits says to spend them only if one holds some When every account was held as set not to spend its credits, the 429 told the user to let an account spend them to go on now. An account that holds no credits is refused by the vendor at 100% all the same, so following that got one more 429. The hint now reads "if an account holds credits, let it spend them", in the credits-only and the mixed message. The gateway's allowance readings carry only the windows, and a Codex reading's balance is "" for none, unlimited and unreadable alike, so a known-empty balance isn't available to drop the hint by. TestCodexNoCreditsEveryAccount checks the new wording in both messages; with the old one it fails with: no "if an account holds credits, let it spend them" in the body (both requests). Follow-up to #974. * usage, docs: a Codex account set not to spend its credits is held by magpie's latest reading The Use credits hint, magpie quota credits' help and the docs said that, turned off, the account's credits aren't spent. The hold goes by magpie's latest reading of the account's windows, which is read again about once a minute, so for a minute or two after a window fills, or while nothing is read yet, a request can still reach the account and spend some credits. Each now says the hold follows that reading, refreshed about every minute (Usage card in en/zh/ja/de, quota help, reference.md, gateway-routing.md). codex-credits (Chromium and WebKit, en/zh/ja/de: 8/8), i18n-keys (1/1), gui-ja (3/3) and gui-de (3/3) pass; codex-credits checks the reworded string has its zh, ja and de. Follow-up to #974. |
||
|
yetone
|
050e629b0a | gateway, provider: a Claude model is asked on Anthropic's Messages where its provider has an Anthropic URL, not Chat (#997, wlj521: 自动好像只会走chat; ReturnTrue on Discord: a relay with an OpenAI and an Anthropic URL had 0% cache hits from Claude models until the OpenAI URL was left empty) — every API's order was Chat first. A request on an API the provider serves was already relayed as it is (a fake relay recording each path: Messages → /v1/messages, Responses → /v1/responses, Chat → /v1/chat/completions, for GLM, GPT and Claude alike, with one URL for three APIs and with an OpenAI URL plus an Anthropic one), but two places fell back to Chat for Claude: usable(), which a request on an API the provider lacks is translated to (Codex's Responses for a Claude model at a Chat+Anthropic relay went to /v1/chat/completions, losing the cache breakpoints the translation to Messages adds), and Provider.Native, the API Pi, omp and droid are wired to ask each model on (route.go's magpieModels), which named Chat for every Claude model at such a relay, so those agents spoke Chat and their cache_control never reached the relay. MessagesFirst (a Claude model by name, where the provider has an Anthropic URL) now puts Messages first in both, beside ResponsesFirst for OpenAI's models. A model the user set "Asked on" for, or one the vendor's list names its APIs for, is as before; GPT and other models keep Chat first; Copilot's Claude, which its list serves on Chat and Messages, is now native on Messages (TestNative updated), the API Claude Code already reaches it on. Not reproduced: a Claude Code /v1/messages request translated to Chat — with either relay layout, a list as new-api answers it, and a key per protocol, it went to /v1/messages with cache_control kept; ReturnTrue is asked for the request's Protocol row. TestClaudeGoesOnMessagesWhereTheRelayHasThem and TestNativeClaudeIsMessagesWhereServed fail without the change and pass; TestAutoRelaysOnTheClientsOwnAPI guards the pass-through for the three APIs; -race -count=5 on them. go test ./internal/gateway ./internal/provider ./internal/catalog ./internal/agent, go vet, darwin, linux (nogui) and windows builds pass. docs/subsystems/gateway-routing.md says the order. | ||
|
yetone
|
a711f428ad |
agent: CodeBuddy Code (Tencent's CLI, codebuddy/cbc, the China edition too) is an agent that uses magpie's models (#980, yujianbinm) — the CLI (npm @tencent-ai/codebuddy-code 2.161.4, one package for codebuddy.ai and codebuddy.cn, CODEBUDDY_INTERNET_ENVIRONMENT=internal) takes models of one's own from ~/.codebuddy/models.json ($CODEBUDDY_CONFIG_DIR), the format WorkBuddy reads, hot-reloaded, and starts a session on settings.json's "model". magpie now writes its models there as WorkBuddy's are written (vendor magpie, key magpie-codebuddy, url the gateway's /v1/chat/completions), keeping the user's own entries, their order, a model turned off and availableModels (magpie's ids added when the list is there), and sets "model" to the pick, the user's other settings kept; one of CodeBuddy's own models, or default, takes magpie's models out again. A new models.json is {"models":[…]} as CodeBuddy's docs give it. workbuddyWrite becomes buddyWrite(agent), the same writer for both. CODEBUDDY_CONFIG_DIR joins agentenv.Vars; cliupdate knows the npm package. TestCodeBuddyCode (user's model, availableModels and settings kept; magpie pick; sync; back to own; default) and TestCodeBuddyCodeNewFile fail without the agent ("no codebuddy agent") and pass; -race -count=5 on the CodeBuddy/WorkBuddy tests. End to end, the real CLI 2.161.4 under a temp HOME with CODEBUDDY_INTERNET_ENVIRONMENT=internal and no CodeBuddy sign-in: magpie codebuddy magpie/mock/pro against a sandbox gateway on 3462, then codebuddy -p with no --model, answered through the gateway from a mock upstream, and magpie's usage counted it under CodeBuddy Code (the CLI sends "CLI/2.161.4 CodeBuddy/2.161.4", so it is told by its key); magpie codebuddy default took it out. A bare-list models.json is read by the CLI too. Not tried with a real CodeBuddy account or a real model vendor. go test ./internal/agent/ ./internal/agentenv/ ./internal/usage/ ., go vet, darwin, linux (nogui) and windows builds pass.
|
||
|
forever
|
a7c4e5ddde |
provider: a Codex account the Codex app still sends for keeps Codex signed in — spend cap or overage with credits, limit_reached alone; a hold survives a failed read (#996)
* provider: a Codex account at a spend cap or past its overage with credits left keeps Codex signed in, as the Codex app's composer still sends for it #966 held such an account (and one whose limit_reached alone was true), following the readiness check Tht in ChatGPT.app 26.930. Tht has one caller, the work-credit-restriction-recovery poller; it isn't the composer's gate. The composer's submit is disabled only by hP (search "n.rate_limit?.allowed!==!1||Jpe(n)||SIe(") and hardBlocked (search "hardBlocked:r.rate_limit?.allowed===!1"): both read rate_limit.allowed alone and let credits (has_credits or unlimited) through before any spend cap or overage. So the app sends for that account, and holding it gains nothing: CodexUsedUp only moves Codex to magpie as provider while Codex is on a magpie model, whose turns already reach magpie through openai_base_url. It only takes the app out of ChatGPT (durable threads, remote control), the loss #966 set out to stop. codexHeld is back to that gate: held when allowed is false, no credits, and not a workspace within its overage (no spend cap, an ordinary reason). Its comment names the build, both gates and why Tht isn't one, each with a string to search for. The spend-cap and overage subcases now expect not held; new subcases pin allowed as the only trigger. Five subcases fail on the merged codexHeld. agent-wiring.md and reference.md say the same. Follow-up to #966. * provider: a Sci, Law, FinServ or Enterprise trial/view-only workspace within its overage keeps Codex signed in codexHeld lets a workspace with no credits through while it is within its overage, as the Codex app's composer does, but the workspace list came from codex-rs's PlanType alone. The app's own plan_type switch for its usage banner (ChatGPT.app 26.930.61225, app-initial) also names sci, law, finserv, enterprise_cbp_trial and enterprise_cbp_view_only, so such an account read held and magpie took Codex off its ChatGPT sign-in while the app still sent. They are added; the comment cites that switch. guest there is a personal plan and stays out, and a plan not listed still counts as no workspace (held). Verification: "Law without credits, within its overage" in TestCodexUsedUpIsWhatTheAppHolds fails without the list change (CodexUsedUp = true, want false) and passes with it. * provider: a held Codex reading with no window at 100% stays held through a failed read A reading kept for when /wham/usage fails dropped Held whenever none of its windows read 100%. That is right for a hold that came with a used-up window which has since started again, but a hold with no window used up (the backend says not allowed, no credits, every window under 100%) has no reset to wait for: the first 503 after it read not held and put Codex back on its ChatGPT sign-in for an account its app sends nothing for. Held is now cleared only when the saved reading had a window used up and none is after the passed resets are applied; any other hold stands till a fresh read. Verification: TestCodexHeldWithNoWindowUpKeptTillAFreshRead (the real Pro reply, credits spent, its window at 40%: a good read, then a 503) fails without the change ("CodexUsedUp = false on the kept held reading, no window used up") and passes with it. TestCodexHeldKeptOnlyTillTheReset still passes; both share their setup now. -race -count=10 passes. * agent, gui, docs: Codex's sign-in notes say magpie steps in while the Codex app blocks the account, not whenever it is used up #981's sign-in notes said magpie becomes Codex's provider "while its account is used up". Since codexHeld, a ChatGPT account at 100% with credits left keeps Codex signed in; magpie steps in only while the Codex app blocks the account (out of allowance, no credits left), and the notes now say that, Always ChatGPT's to match, in English, Chinese, Japanese and German. agent-wiring.md's sign-in line and reference.md's Codex paragraph say when the app holds an account as codexHeld reads it: OpenAI no longer allows it and it has no credits left, a workspace still within its overage excepted; at 100% with credits Codex stays signed in. Verification: codex-signin-always (Chromium and WebKit, en/zh/ja/de, 1100 and 440px) 8/8, i18n-keys 1/1, gui-ja 3/3, gui-de 3/3. git grep finds the old English notes nowhere under internal/gui/tests or internal/gui/assets. |
||
|
forever
|
8005f17551 |
provider, codex: a ChatGPT account at 100% with credits left keeps Codex signed in (#966)
* provider, codex: a ChatGPT account at 100% with credits left keeps Codex signed in — magpie becomes its provider only while the Codex app itself holds the account magpie made itself Codex's provider (model_provider = "magpie", #540) whenever any of the active ChatGPT account's windows read 100%. A Pro account at 100% on its week with credits left keeps working in the Codex app: the backend answers every turn (about 490 200s in one day's usage log at 100%), yet magpie moved Codex off it, and as a provider without requires_openai_auth the app lost its ChatGPT state ("Sign in to ChatGPT to start a durable thread", no remote control). CodexUsedUp now reads codexHeld, which mirrors the Codex app's own composer block (ChatGPT.app webview bundle, hP and its helpers): the backend says the account isn't allowed (rate_limit.allowed = false), it has no credits (has_credits / unlimited), and it isn't a workspace still within its overage (overage_limit_reached = false, no spend cap, an ordinary rate_limit_reached). Window percent never decides it. Where the app goes by what /wham/usage can't show (a statsig gate, the gpt-reserve fallback, Team's reserve experiment that ignores overage), it counts as held: a wrong move costs ChatGPT extras, a missed one every turn. A reading kept through a failed read (keepLast) stops saying held once its used-up window has started again, as its usage does. NextLogin's account rotation and its thresholds are unchanged. A user stuck on the old move (codex.out = 1) is put back beside the sign-in by the next Sync, as #540 already does once the account has room. Verification: - TestCodexUsedUpIsWhatTheAppHolds (real /wham/usage replies, ids replaced) fails on the old trigger: 7 subcases, "CodexUsedUp = true, want false". Each workspace guard (spend cap, reason, overage, plan list, Team reserve) was mutated and fails its own subcase. - TestCodexHeldKeptOnlyTillTheReset fails without the quota_last change. - The real Pro account (7-day window 100%, ~28k credits, allowed false): CodexUsedUp true before, false after. - go vet ./...; go build (darwin), GOOS=linux -tags nogui, GOOS=windows; go test -tags nogui ./... under a sandbox HOME; -race -count=20 on the new and related Codex tests. - Not run: a live Codex app turn on an account truly held (none at hand), Windows/WSL runtime, GUI suites (no GUI change). * provider: a Codex account at a spend cap or past its overage is held, credits or not; limit_reached counts as not allowed codexHeld let credits through before the spend cap, so a Team seat at its cap (spend_control.reached, allowed false) with has_credits read not held and magpie left Codex on an account the backend refuses. The app's readiness check (26.930.61225, app-primary) returns limited on spend_control.reached or credits.overage_limit_reached before it looks at credits, and treats rate_limit.limit_reached like allowed false; held now reads the same. A spend cap with the rate limit still allowed (a workspace's included usage) stays not held. |
||
|
forever
|
b37ac53bef |
codex: a switch for whether an account spends its credits (#974)
* tui: show a ChatGPT account's credits beside its windows The Usage page printed only the balance for an account that had one, so a ChatGPT account holding credits lost its 5-hour and weekly windows there. The balance now follows the windows, as on the app's cards and in magpie quota. * accounts: tell a ChatGPT account's credits magpie accounts left out the credits an account holds, which magpie quota and the Usage page show. Its rows now carry them, in the line and as balance in --json. * codex: a switch for whether an account spends its credits A ChatGPT account holding credits keeps answering once a usage window is used up: the vendor spends the credits, and a task goes on. That stays the default. Each Codex account now has a say in it (Usage card and menu bar panel: Use credits; magpie quota credits <account> on|off; settings' codexNoCredits). Turned off, the gateway holds the account at 100% of a window, as a usage cap holds it at its share, so the other accounts, groups and fallbacks take the request and no credits are spent. With none left the request gets a 429 naming what holds each account and how to go on, unless the account spends its resets by itself and its week is used up: then a reset is spent first, whether every candidate was held or the last one tried was refused. A cap set on the account takes precedence. A reset made now forgets the account's cached allowance, so neither a cap nor this hold outlives the windows it started again. The switch is routing's only: which account Codex is signed in to is unchanged. The Routing page tells why such an account was left out, and magpie quota, magpie accounts and the TUI mark credits not spent. * usage: an auto-reset switch keeps by its first line The auto-reset row centred its switch on its words, so the switch moved when they rewrapped on a click, and it sat lower than the Use credits switch beneath it. Both now keep the switch by the first line. * gui tests: quota-curve expects the Use credits row to close a Codex account's section The credits switch adds a row after the Auto-use one, so the account after a Codex account follows the curve, the Auto-use row and then the Use credits row. |
||
|
yetone
|
5839e08189 |
dsh: the gateway key also goes into dsh's own key store, which the desktop app reads (#969, pan17: in the DeepSeek Harness desktop app every turn failed with llm-pi-ai: no credential for provider route "magpie"; its profile resolves MAGPIE_GATEWAY_KEY, which is not set — store MAGPIE_GATEWAY_KEY through the credentials service (the web Models page writes it) or export it (MISSING_CREDENTIAL), while magpie showed dsh connected) — the route was in the desktop profile (magpie writes every profile; the GUI names only the first, profiles/web, which read as "magpie wrote the npm dsh's config"), but magpie put the key only in ~/.dsh/.env. In dsh 0.2 the .env files are layers the product CLI's boot (dsh-app-boot) loads; dsh-credentials-local resolves inherited environment > $DSH_HOME/.credentials.yaml > project .env > home .env, and "a composition the product CLI did not boot has only the inherited environment as its layer". So the desktop app never saw the key. magpie now also writes refs.MAGPIE_GATEWAY_KEY into ~/.dsh/.credentials.yaml, dsh's own store, which its Models page writes and every dsh reads. Details: a new store is made owner-only, version 1 (dsh refuses a store other users can read); the user's other refs, records and comments are kept; a different key of the user's under magpie's name is left alone (the check already reports it); a store in dsh's pre-release flat layout isn't touched; going back to dsh's own models takes magpie's key out. The check now asks for Apply again when the store lacks the key; a dsh wired by an earlier magpie gets it from the catalog sync magpie runs as it starts. The output of a fresh write and a merge into a store with refs, a grant record and a comment both parse with dsh 0.2.0-rc.2's own parseCredentialsDocument. TestDshDesktopGetsTheKeyFromItsStore (web+desktop profiles as on the reporter's machine) and TestDshStoreOfTheUsersOwn fail without the change and pass; -race -count=5 on the dsh tests. Fixtures that stood for "wired" with .env alone now hold the store too. Not tried with the real desktop app (not installed here; the reporter is on Windows); they're asked to confirm. go test ./internal/agent/, go vet, darwin, linux (nogui) and windows builds pass.
|
||
|
forever
|
7f45f45cb5 |
codex: a sign-in kept on ChatGPT when its account is used up (#981)
Codex's sign-in, ChatGPT, keeps Codex signed in to ChatGPT with magpie's models beside its own, but once the ChatGPT account is used up magpie makes itself Codex's provider (#540): the Codex app sends nothing at all on an account it knows is out, a magpie model's turn included. That move went unsaid, and a user who chose ChatGPT expected Codex to stay there. ChatGPT now says it, and a third way, Always ChatGPT (login "chatgpt"), never makes the move, by a pick or by Sync; choosing it puts a Codex moved before back beside the sign-in. What it costs is said beside it: the Codex app may send nothing till the account has room, while Codex CLI's turns still reach magpie by the base URL, its routing and other accounts serving them. |
||
|
yetone
|
e0bf3e61ed | catalog: a model the provider's catalog doesn't list is named as the other providers name it (John on Discord #feedback: GLM Coding Plan and ZCode name the same models in different case, in the provider list and the group picker) — the Coding Plan's /models (open.bigmodel.cn and api.z.ai, read with a real key) gives ids alone, glm-5-turbo, glm-5.3-flashx …; catalog.Decorate names only those Zhipu's models.dev entry (zhipuai) lists, so glm-5-turbo kept its id as its name beside ZCode's GLM-5-Turbo. models.dev's load now keeps each model's name as most providers serving it give it (a name that is only the id casts no vote), catalog.NameOf reads it by bare id in any case, and catalog.Named fills it in for a model still named by its id: in Available's live list and for a pick the list doesn't have. Ids, and what is sent upstream, are unchanged; a name the user gave stays theirs (Catalog's Name, with the new one as Default); an Azure provider is left out, its deployments named as their owner named them. TestModelNamedAsElsewhere (the Coding Plan's real ids, a user name, an Azure deployment) fails without the provider change and passes; TestNameOf is new. TestSearcherChosen read whatever catalog an earlier test had left loaded, and now resets it: with none, its lists' models go by their ids, as it expects. go test ./internal/catalog/ ./internal/provider/ ./internal/gateway/ ./internal/gui/ . pass; -race -count=5 for the two new tests; go vet, linux(nogui)/windows builds pass. No GUI change (the GUI and the group picker show name || id). | ||
|
yetone
|
8c71cd27f9 |
quotas: a computer using another's magpie (remote-magpie) shows that magpie's quota cards (莫 on Discord: the second computer had the models and groups but /v1/magpie/quotas was empty, so Usage, the menu bar and magpie quota showed nothing) — each named with the remote ("Codex · Office", id office/codex, from: Office) and kept in its kind (subscription, plan, balance), on the Usage page, the tray, the TUI and magpie quota (which matches by the remote's id or name); their history comes with the local one. Only the computer holding the sign-ins asks vendors: it answers the new GET /v1/magpie/quotas/cards from what it has kept (CachedCards, never a read, whatever the age), asked here at most once in 30s; a card's refresh here POSTs /v1/magpie/quotas/refresh (that card, or every card from the remote's own card), which the remote does at most once in 30s per card. A remote keeps showing its last cards when it can't be reached; with none its one card says why (nothing read there yet, or a magpie too old to share — "update magpie there", zh/ja/de added). Cards from a third magpie aren't passed on, and the refresh path refuses them (400); a Codex reset or check-in isn't offered on a remote card. Same auth as /v1/magpie/quotas (loopback, or LAN with the key).
Verified: provider tests (fake remote: names/kinds, buttons stripped, third-magpie cards dropped, one ask per 30s, refresh paths, unreachable keeps last cards, 404 → update card, cache-only CachedCards, histories) and the gateway test (an in-process gateway with a fake balance vendor counting hits, asked through a remote-magpie provider: nothing read until a refresh, 5 card asks read nothing, two refreshes of a card read once, a remote card's refresh 400, another machine without the key refused) pass with -race -count=20; go test provider/gateway/gui/tui/root, vet, linux and windows builds pass. Two sandbox gateways (3481 with a fake balance vendor, 3482 with it as remote-magpie): magpie quota on the second showed the "nothing read" card with 0 vendor hits, then office/bal "Bal · Office" $12.00 after one refresh (1 hit), 10 more asks 0 hits, two card refreshes 1 hit. usage-remote-cards (names, translated remote errors, refresh ids) passes in Chromium and WebKit, en/zh/ja/de and fails without the app.js change; i18n-keys, gui-ja, gui-de, usage-card-refresh, usage-refresh, quota-reading-again pass. Not tried with a real second computer. |
||
|
yetone
|
ccf5e5a1cb |
docs: VSCodium's row in the agent reference (#926) — VS Code Insiders had one, VSCodium (merged in 2f15623e) didn't: its files under VSCodium/User, its own token magpie-vscodium, and the Chat features it needs turned on, as its Notice says.
|
||
|
Zhizhen He
|
9fcfbbdfee |
provider: back up unreadable saved accounts with valid JSON (#965)
A cold-start account add could replace logins.json without keeping its credentials when the JSON was syntactically valid but could not decode as saved accounts. Match readLogins' typed decoding in the backup check, so invalid field types and a wrong root type are kept aside before a write. Readable account files still need no backup. TestUnreadLoginsFieldTypesKeptBeforeWrite fails without the change because no original-file backup is made for a string boolean, invalid time or object root. The fixed cases and the readable-file control pass, including five race-enabled runs. Update the providers/accounts failure contract. go vet, the full nogui Go suite, the native macOS build and Linux/Windows cross-builds pass under a temporary HOME with pinned Go caches. |
||
|
july_lu
|
47c2382467 |
gateway: a gateway key can be held to some accounts (#905, LCorleone) — a key could burn any account a provider had: two coding plans of one vendor, and a key given to someone had them both. A key now keeps an optional list of accounts and keys (caller-keys.json "accounts", none = every account, so older files read as before): "<provider>/<account>", an account by its stable id — the login's, set once it is written and kept through renames (logins.json's savedLogin id, written by every write and stood in for by one made of the name until then, so an entry made before stands), a key by its fingerprint — every one a provider has when the list is set, and one gone later (a key rotated, an account signed out) kept as it is, matching nothing, holding the key closer, never wider. The command line and the menu name an account by who is signed in and keep its id. Routing holds a plan to the key's accounts beside its models: a candidate whose account the key may not use is left out — through a routing group the key names no less, for naming a group is not naming its accounts — the plan's order keeping step and its left-out list marking what the key held out (Weighed's held); magpie's own calls for the key — a web search, a picture described, a Codex title — are of the models the user picked, so the models don't hold them, but their spend lands on an account all the same, and the accounts hold them too. When every account or key a model has is one the key may not use, the request is refused with a 403 in the API's own error shape naming the model and the accounts the key may use, logged as a rejected call: after a usage cap's 429 and before an account barred for the model's, itself before the no-member 404. /v1/models and the Anthropic and Gemini lists show the key only the models an account or key it may use serves (a provider's account set not to serve one, #474, is none of the key's); a provider with no account and no key (a local ollama) is one the key names no account of — its models stay listed and its asks pass — while an entry kept after its provider lost its last account or key serves none, holding the key closer. The embeddings, images and videos endpoints hold their candidate to the key's accounts the same way, and counting tokens counts on those alone (the local estimate where it may use none). System One asks its decision model of an account or key the key may use — and sends on that key, of those in use, not the provider's first, which a key held to a later one was spent on; the videos and images keyed paths send on one the key may use too, held to a later key no longer refused for the first alone. Set it in the app's menu the models are picked in — the accounts after the models, an account by who is signed in with their plan in the note, a key by its fingerprint, what the CLI kept that no provider has now kept as "Not signed in now" — or magpie gateway-key accounts <id> codex/me@example.com openai/<key id> (all takes it off); gateway-key list has an ACCOUNTS column. en/zh/ja/de, the German "{n} accounts" main already had left to it rather than written twice. The images API's fan-out over a subscription's accounts is held to the key's accounts as one: one of the key's whose plan refuses to draw no longer hands the pen to an account it may not use, and the second in the order, when it is the key's, draws what the first may not (drawOnAccounts filters the candidates, the account pinned to with the account header told plainly when the key may not use it). The Routing view's left-out list says an account the key held out for what it is, not that its plan lacks the model, in Chinese, Japanese and German too; the key's badge names its accounts by who is signed in, not by the stable ids it keeps. (#932)
|
||
|
tsuixl
|
d418b25424 | fix(provider): scope quota deduplication to GLM and ZCode (#953) | ||
|
tsuixl
|
db55bc8b7a |
gui: reject unknown Codex auto-review models from known providers (#938) (#943)
Resolve deliberately accepts arbitrary model names under an existing provider. The auto-review setting consequently accepted fake/missing and fake/, replacing a valid reviewer with one that fails when Codex requests approval. Validate against the served catalog at the settings endpoint. Keep model and group choices, unlisted providers, whitespace trimming and clearing. Rejected values leave the saved reviewer and model-list tag unchanged. TestCodexAutoReviewSetting fails against the upstream API with fake/missing and fake/ returning 200, and passes with the fix. Focused auto-review tests, go vet ./..., the Windows build and Linux nogui build pass. The full Windows suite has failures also reproduced with upstream production code; details are recorded in the PR. |
||
|
|
2cc663d0a2 |
gui: protect unsaved edits and confirm destructive actions (#820)
* gui: edited forms ask before they are discarded, removals ask before they take effect, and the header keeps its first layout — Cancel, Escape, the backdrop and a page change could throw away a provider's draft, and several account, key, plugin and library removals took effect at once. Modified provider, settings, library and routing forms now ask before discarding; unmodified forms still close without asking, and refresh or closing the browser tab uses its leave confirmation. Removal and discard confirmations are in-app dialogs over the intact editor, centered, with Cancel focused first, Tab kept inside, Escape canceling and focus returned afterwards; destructive buttons have readable foregrounds in light and dark themes. Text and connection settings have Save/Cancel rather than saving on blur; simple switches still save at once. Editors associate labels and help with fields, make the background inert while open and keep focus through redraws; navigation keeps browser back/forward history and its current-page state, errors remain until dismissed or replaced, and focus and validation can scroll into view. Mobile settings tabs have larger targets, fields use 16px text and page zoom stays available. layout.js applies mode and platform before the header paints, theme.js applies the saved text size before styles, and mode-specific window controls stay hidden while app.js downloads. zh/ja/de strings added. routing-shape's global .rt-day selector selected the hidden By session button on WebKit; its history click now stays in .rt-days. ux-safety covers unchanged and modified closes, canceled and confirmed removals, Escape, backdrop, modal focus, light/dark centering and button contrast, explicit saves, browser history and sync-form discard. Rebased onto upstream/main |
||
|
yetone
|
5a4c69fbdc | docs: contributors.md lists lunar-me under authors reviewed with extra care (the maintainer chose not to block), with the evidence and what the extra care is | ||
|
yetone
|
fa7a0f23a8 | gateway: a streamed reply whose vendor goes quiet keeps its agent alive on a timer of its own, held or passed, so a proxy in front doesn't end it (#947, jorben) — a vendor that sent its 200 and response.created and then nothing had the stream held for its first content with no event to scan, so the agent got no headers at all until it spoke again, and Cloudflare in front of a remote magpie ended the request at 125s (524); a translated reply quiet mid-way was kept alive only as the vendor sent something, and the proxy reset it. holdWriter.watch now runs beside every streamed try (it was only Group.FirstToken's watchFirst): past keepHeldAfter it sends a held try's agent the stream's 200 and SSE comments (keepAlive), none of the try, so another account may still answer in the same stream; once passed, a comment goes between two of its lines after keepaliveEvery of quiet; it stops after keepaliveLongest with nothing from the vendor, and Gemini streams get none (#934). Covers every protocol, relayed or translated. quiet_keepalive_test.go is new (held, mid-reply, failover after keepalives, the 5-minute cap, Responses/Anthropic/Chat relayed and Anthropic from Chat) and fails without the change. go vet, go build (darwin, GOOS=linux nogui, GOOS=windows) and go test -tags nogui ./... under a temp HOME pass (TestUserPath in internal/proc failed once under the full run and passes alone). | ||
|
yetone
|
9ae796d5b5 | 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 | ||
|
yetone
|
963d8d9d88 |
gateway: a provider that turns Codex's image tool away with a bare 400 is asked again without it, and isn't offered it again once that works, so a plain chat no longer breaks on it; a ChatGPT sign-in, openai.com and a Codex backend that takes it still get it (#949, cjyrainbow)
Since #870, magpie's provider in Codex's config carries x-openai-actor-authorization, so Codex offers its image_gen namespace tool on every request. A vendor's Responses API that can't take it, a relay's included, answered "bad response status code 400" to "只回复 OK". After a bare 400 (one that names no field or message magpie already knows to drop), a provider other than a ChatGPT sign-in or openai.com is asked once more without the tool. This works both passed through (the namespace) and translated (image_gen__imagegen flat). If the retry answers, the provider is marked unfit for tool:image_gen. If it doesn't, the tool goes back and the vendor's 400 stands, and the cache-key guess runs on the request as it was. The header stays as #870 wrote it. image_tool_test.go is new. Its fixture is the image_gen tool Codex 0.160.0 sent to a capture server with magpie's provider table and catalog. TestImageToolLeftOutWhereRefused (translated, passed through) fails with the reporter's 400 when gateway.go is reverted, and so does TestImageToolKeptOverAnotherRefusal. TestImageToolKeptForChatGPT fails when the ChatGPT exemption is dropped. docs/subsystems/gateway-routing.md has the rule. go vet, go build (darwin, GOOS=linux nogui, GOOS=windows) and go test -tags nogui ./... under a temp HOME pass. |
||
|
yetone
|
aab93f9fa8 | gateway: in turn, a new conversation goes to the model or account the fewest live conversations are on, so two sessions of one routing group kept for the session no longer share a model (#946, Moody-Sin) — in turn counts requests, not conversations, so a second session started after the first had sent an even number of requests went to the model the first was kept on. leastHeld counts the conversations of the scope answered in the last 30 minutes per key/account and model and puts the least held first; ties, resting ones and a group with a group in it keep routing's order. TestRotateSpreadsSessions is new and fails (after 2 and 4 requests) without the change. go vet, go build (darwin, GOOS=linux nogui, GOOS=windows), the gateway package and go test -race -count=20 of TestRotateSpreadsSessions/TestAffinity pass; go test -tags nogui ./... under a temp HOME failed only TestWSLProbeFindsBunOmp, TestProvidersAnswerWhileListsComeIn, TestUserPath and TestClaudeSignedOut under the full run's load, each passing on its own. | ||
|
yetoneandClaude Opus 5.5
|
303819c583 |
docs: LESSONS.md keeps what the nightly review of merged work finds, and agents read it before changing code
The first review covers 2026-10-05's 220 commits (~170 releases): about 40 fixed something released that day or the day before. The lessons are grouped by kind (misread report, fix one sample of a class, user files, thin verification, red tests and releases, merging and closing), each with its evidence. Three that recurred dozens of times move into docs/code-standards.md: a fix reaches every sibling of the bug, a test red on main is fixed rather than used as a baseline, and a release needs a finished green CI run, not a cancelled one. AGENTS.md points at LESSONS.md and CLAUDE.md loads it. Docs only; no code or test changes. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> |
||
|
yetone
|
4c170cbad6 | library, gui: DeepSeek Harness is listed under Library › RTK with why RTK has no hook for it, not left out (lc on Discord) — RTK rewrites the shell command an agent is about to run, and dsh's hooks can only allow or deny one (its Claude Code bridge drops updatedInput; deepseek-harness's pre-tool-input-rewrite is only proposed), and rtk 0.51's init has no --agent dsh (rtk-ai/rtk#3847; the open #3934 only adds AGENTS.md text, which rewrites nothing). So the RTK tab left dsh out and it read as magpie not seeing it. rtkNoHook names it with the reason: the row has a No RTK hook tag (zh/ja/de) and a switch that can't be turned on, magpie library rtk prints the reason, and on/off for dsh answer it instead of "rtk has no hook for dsh". TestRTKNoHookListed and library-rtk-nohook.test.cjs (Chromium, WebKit, en/zh) are new and fail without the change. go vet, go build (darwin, GOOS=linux nogui, GOOS=windows) and go test -tags nogui ./... under a temp HOME pass (TestProvidersAnswerWhileListsComeIn and TestUserPath failed once under the full run's load and pass on their own). | ||
|
yetone
|
a5df344e43 |
docs: code-standards gets the acceptance criteria a change must show before merge or release and the PR review patterns, and docs/subsystems covers gateway routing, agent wiring, providers and accounts, the library and the GUI shell (Junjie Zhou on Discord)
code-standards.md: a failing test before the change (a real FAIL, not a compile error), tests under a temp HOME with GOPATH/GOMODCACHE/GOCACHE pinned and never a live agent config, vet/build (linux nogui, windows)/test with pipefail, GUI tests in Chromium and WebKit with gui-ja/gui-de, real-account checks in a sandbox, the UI rules; a PR merges only after it is run merged onto main and with --match-head-commit; a release counts only with the tag on main, 16 assets and Latest. The review section is distilled from recent PR reviews (#706–#931). New references, each following the README's format and linking real source: gateway-routing.md (plan/planGroup, rests, sink, affinity, attempt/translate), agent-wiring.md (Agent fields, ConnectHow, applied.json drift, stash, DisconnectPreview, Reseat/Rewire, WSL twins and ListsFor), providers-accounts.md (providers.json, keys, Accounts, token refresh, logins, groups, Quotas), library.md (change/sync, instructions, MCP formats, skills link/copy, backups, RTK), gui-shell.md (Run, startBackend, Handler/held/revalidated, magpie web, gateway mode, nogui). Every link and backticked identifier was checked against the tree at origin/main. Docs only. |
||
|
yetone
|
1330b9660e |
agent: VS Code Insiders is an agent of its own, its Chat given magpie's models in Code - Insiders/User as VS Code's is in Code/User (wani on Discord)
vscode.go's agent is now one per build (vscodeKind): VS Code as it was, and VS Code Insiders, id vscode-insiders, its User folder Code - Insiders beside Code on the Mac, Windows and Linux, its binary code-insiders. Insiders' chat names itself GitHubCopilotChat as Stable's does, so it has no UA of its own: its models send the token magpie-vscode-insiders, which the gateway reads first, and its requests are its own in Usage while Stable's stay Stable's. Connecting one writes nothing of the other's. TestVSCodeInsiders fails without the change (unknown agent "vscode-insiders"). go vet, go build (GOOS=linux nogui, GOOS=windows) and go test -tags nogui ./... under a temp HOME pass. |
||
|
yetone
|
926bcaa379 |
docs: code standards distilled from PR reviews, linked from AGENTS.md (Junjie Zhou on Discord)
docs/code-standards.md gathers what reviews keep asking for: a change holds on its whole path and does only what its goal needs, a fix comes with a test that fails without it and uses real inputs, tests check behavior and stay out of the real machine, the checks run before a merge, Go's any, appdir.Getenv and agentenv.NotPaths, the GUI's t()/i18n, no native select, no click scroll and no left-border stripes, and the commit message style. Junjie Zhou's six review rules from Discord are its first two tables; the rest is from merged PR reviews (#901, #922, #924, #926, #930) and the GUI tests. AGENTS.md links to it. |
||
|
yetone
|
fbaf27bce1 |
agent: dsh's web search goes through magpie while dsh is on one of magpie's models (Packing1 on Discord)
dsh's web search is a plugin of its own, web-search-deepseek, which signs each search to DeepSeek's Anthropic API with DEEPSEEK_API_KEY, so a dsh that reaches its models through magpie alone failed every search asking for that key. While dsh starts on a model of magpie's, magpie writes a marked web-search-deepseek entry in each profile: the gateway's /v1 as baseURL, MAGPIE_GATEWAY_KEY as apiKeyEnv and that model. The gateway answers the plugin's web_search_20250305 request as Anthropic does, by the model's own search or magpie's (web_search_tool_result blocks). A row of the user's, or a DEEPSEEK_API_KEY dsh has in .env or its key store, is left as it is. The entry goes with dsh's own model or Disconnect, and moves with the gateway's address. The row's Notice says when magpie has nothing to search with. TestDshSearchThroughGateway is new and fails without the change. Tested end to end in a sandbox (own HOME and DSH_HOME, gateway on 3493, the real DeepSeek account): real dsh 0.2.0-rc.2 headless called web_search, got eight results through magpie, and answered https://golang.google.cn/blog/go1.26; magpie dsh default took the entry out of all three profiles. go vet, go build (darwin, GOOS=linux nogui, GOOS=windows) and go test -tags nogui ./... under a temp HOME pass. |
||
|
yetone
|
055f17883f | gateway: a Claude subscription conversation the client sends back rewritten goes on in the run that had its last turn, and Claude Code's temp images go with their session (#912, margbug01) — Alma takes the [Context: …] block out of its last user message once the turn is over, the <alma_notification> block out of the end of the reply, and picks the tools for each turn, so turnKey, which hashes all of it, never matched and every turn started a new claude -p told the whole conversation, written to the prompt cache again with its images. ended keeps a looseTurn beside the key: the settings without the tools, the conversation before the last turn hashed, and the last turn's messages one by one. When the exact key misses, rewritten takes the one idle run or saved session whose looseTurn has the same owner, settings and earlier turns, the same roles, tool calls and results in the last turn, where a user message only had one part taken out (cutFrom) and the reply is a non-empty start of what the run said. Two that could be it start a new run, as does an idle run not told a tool offered now (offers) or a saved session one of whose tools is gone (toolsCover). Claude Code's <CLAUDE_CODE_TMPDIR or /tmp>/claude-<uid>/<work project>/<session> folder, where it keeps the images it was given, is removed with the session (removeSession), and the sweep removes those a stopped gateway left once their session file is gone and nothing in them changed for a day; CLAUDE_CODE_TMPDIR joins agentenv.Vars. Old images are still sent to a new run: replacing them would change what the model sees. docs/subsystems/claude-subscription-bridge.md is new. claude_rewritten_test.go has a case for each relaxation (failing before the change) and one for each rule that keeps another conversation out (each failing with that rule taken out). Tested for real with the owner's Claude Max account in a sandbox HOME: turn one asked with a [Context] block and two tools, turn two sent it back with the block taken out, the reply cut short and one tool, and went on in the same claude process ("goes on in its run", cache_read 1932). go vet, go build (darwin, GOOS=linux nogui, GOOS=windows) and go test -tags nogui ./... under a temp HOME pass. | ||
|
yetone
|
3a30ac87c2 |
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)
v0.1.1032 counted a 1-hour cache write left out at 2× input for every model, so gpt-6-astra priced 10,50,1,12.5 showed "$20 (1 hour) at 2× input", a write OpenAI has no price for. OneHourFor gives a Claude model's price, listed or given by the user, its 2× input; any other model's 1-hour writes count at the 5-minute price, magpie model price shows only its cache write, and the app shows the 1-hour box only for a Claude model or one priced with one. |
||
|
yetone
|
df95ac6bc2 |
docs, site: Integrating your app or agent with magpie, at docs/integrating.md and usemagpie.ai/docs/integrate (#918, Magixyne)
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). |
||
|
yetone
|
bc00ee1df2 |
plugin, provider: a program a plugin starts has magpie's proxy, and a CLI login with no link says why (𝕏 on Discord)
The Grok plugin's sign-in said only "grok login gave no link to open". The plugin host has magpie's proxy only as MAGPIE_*_PROXY, so the `grok login` the plugin runs went out with none, where the built-in's had it (netproxy.Env); where x.ai is reached only through a proxy, it failed. host.js's spawn wrapper now gives a started program HTTPS_PROXY and HTTP_PROXY (the account's own proxy, none for direct, else magpie's) when the plugin set none. grok 1.0.46, unable to reach x.ai, prints "Error: error sending request for url (https://auth.x.ai/oauth2/device/code): …", whose URL the built-in's runCLISignIn took for the page to open; a line saying error gives no link, and a login with none ends with the CLI's last line. The plugin does the same from 0.1.8, which the grok mover now asks for. plugin_cliproxy_test.go and TestCLISignInSaysWhyNoLink fail before this. Checked with grok 1.0.46 itself through the plugin host and the published plugin's code, given a proxy that refuses: the CLI goes through it and the error names what it said. |
||
|
yetone
|
11a2d359a1 | agent: VS Code's magpie models and default model go in each of its profiles too, so a window on another profile lists them in Chat (TJHHHH on Discord) | ||
|
yetone
|
71d2da1f42 |
catalog, usage, gateway, gui: a price can have a long-context tier and a 1-hour cache write, and the price boxes take decimals (PAMI on Discord)
OpenAI bills gpt-6-astra, gpt-6.1-sol and gpt-6-luna over 272K input at 2× input and cache and 1.5× output, for the whole request. A price now has tiers: `magpie model price <m> 10,50,1,12.5 --tier 272k 20,75,2,25` (--tier can repeat). A tier applies when input + cache reads + cache writes is over its size, so 272,000 is not over and 272,001 is. The built-in prices take tiers only where models.dev lists one (cost.tiers of type "context"), and it does list one for those three. The ledger, each request and OTLP are costed at the tier the call reached. Session and day totals sum many calls, so they stay at the base price.
Anthropic bills a cache write kept for an hour at 2× input and one kept for 5 minutes at 1.25×. Its usage reports which is which in cache_creation.ephemeral_5m/1h_input_tokens. The gateway (API and Claude subscription) and Claude Code's transcripts now keep that split. A price's fifth part is the 1-hour write. When it isn't given, it is 2× input: that is Anthropic's rule, and only Anthropic reports 1-hour writes. Claude list prices carry the 2× too. cache_write_tokens is still the total, and the usage CSV adds cache_write_5m_tokens and cache_write_1h_tokens at the end. The app shows the split on a request's Cache and on the usage tooltips. Old prices and old records, which have no 1-hour part, read as before. The sessions cache (18) and the call cache (calls-v8) are re-read once.
In the GUI, the price boxes were number inputs and dropped what they didn't parse ("0,25"). They are now decimal text boxes that take both "0.25" and "0,25". A model's price row has a 1-hour box (empty means 2× input) and a quiet Long-context price row. That row shows the list's tier greyed in, or sits behind a link when the list has none. A bad size is refused by name. en/zh/ja/de.
Tests:
- New: TestPriceTiers, TestCostSplit, TestPriceJSON, TestModelPriceTiers, TestModelPriceTierCmd, TestAnthropicCacheWriteSplit and TestClaudeCacheWriteSplit. The ledger CSV test expects the new columns.
- model-price-tiers.test.cjs is new; model-price-edit and provider-price-rate are updated. All of them fail against the old assets and pass in WebKit. Chromium couldn't be launched here.
- go vet, go build (darwin, GOOS=linux nogui, GOOS=windows) and go test -tags nogui ./... under a temp HOME pass.
|
||
|
yetone
|
9dda306a33 |
provider, gateway: a provider's header.anthropic-beta is added to the betas the agent asked, not put in their place (PAMI on Discord)
`magpie provider set <id> header.anthropic-beta=…` replaced the betas each request carried: provider.Sign wrote the user's headers over what the gateway had set, so Claude Code's own betas (claude-code-…, interleaved thinking, 1M context's context-1m-2025-08-07 for a [1m] model) and fast mode's were dropped, and a name typed in another case went out as a second anthropic-beta line beside the gateway's. anthropic-beta is now a list header (provider.ListHeader): Sign merges the user's value into the request's (provider.MergeList: the request's items first, then the user's, each once, empty ones left out, one line under the name as typed). Every other header of the user's still replaces magpie's, as before. The gateway then fits the merged list as it fits the agent's (fitUserBetas, after Sign): a beta the provider has refused (400 Unexpected value(s) `x` for the `anthropic-beta` header) is left out from the retry and from then on, the user's own as well as the agent's; one it takes is always sent. magpie adds no 1M beta of its own: Claude Code 2.1.289 itself sends context-1m-2025-08-07 for a [1m] model to any base URL (its long_context beta is asked when the model matches /\[1m\]/ and is among those kept for third-party endpoints), magpie writes 1M models into Claude Code marked [1m], and the gateway passes it on. Per-endpoint header sets were left out: one set of headers rides on every request to a key+URL provider. docs/reference.md says how header.* works and that anthropic-beta adds. TestSignMergesListHeaders (internal/provider: merged in order, deduped, the request's line not kept beside it, another header still replaced) and TestUserBetasMergeWithTheAgents (internal/gateway: a relay that refuses one of the agent's betas and one of the user's gets the agent's then the user's, both refused ones dropped on the retry and not sent again) are new and fail without the change; TestUserBetasAlone (the user's betas sent on a request with none) passes either way. go vet, go build (darwin, GOOS=linux nogui, GOOS=windows) and go test -tags nogui ./... under a temp HOME pass (internal/provider failed once under load in the first full run and passed in the second). |
||
|
yetone
|
2a57b7bb60 |
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)
In WSL, with only magpie tui and Cursor's subscription, Claude Code said ECONNREFUSED. The terminal set agents to the gateway but never served it, and nothing listened at 127.0.0.1:3425 unless the app, magpie web or magpie serve ran. magpie tui now serves the gateway in its own process while it is open, as the app does, whenever no magpie answers at its address. One that does (the app, magpie web, magpie serve) keeps it. The terminal looks every 15s and takes the gateway up once that one is gone. The status line says "● gateway <url> · served while magpie tui is open" when it has nothing else to say, or "✗ gateway not running: <why>" when the port couldn't be had. On quitting after serving, it says the gateway stopped with it and what serves it otherwise. The usage text and docs/reference.md say so too. Tested in a sandbox HOME on port 3486 with a real DeepSeek key: magpie tui alone answered /v1/models; Claude Code (sandbox HOME) set to deepseek/deepseek-flash ran a Bash tool turn through it; the status line showed the gateway; q printed the note and freed the port. TestTUIServesTheGatewayWhenNoneDoes (serves, status, lets go at quit) and TestTUILeavesTheGatewayToAnotherAndTakesItUp (leaves another magpie's gateway alone, takes it up once it is gone) are new and pass 3x under -race; they don't build without the change. go vet, go build (darwin, GOOS=linux nogui, GOOS=windows) and go test -tags nogui ./... under a temp HOME pass. |
||
|
yetone
|
528d6c12dc |
agent, gui: Codex left on model_provider = "magpie" with no [model_providers.magpie] loads its config again, and connecting with nothing in magpie says what to do, in the reader's language (Tystem on Discord) — the Codex app said "无法加载 config.toml … Model provider magpie not found", magpie showed Codex as not connected on "deepseek-flash", and its switch answered only "Codex can't be connected to magpie", in English. Codex looks model_provider up in [model_providers.*] as it loads config.toml (codex-rs: "Model provider {id} not found"), so the key without the table keeps it from loading any config, a new thread too, not just an old one. magpie never writes one without the other: it takes model_provider out whenever it steps out as the provider (disconnect, Unwire, a model of Codex's own, Join) and keeps the table so the threads started on magpie still open. That is unchanged, and TestCodexSteppingOutLeavesNoHalfState now covers it. Another tool or a hand edit had taken the table away. Sync, at magpie's start and whenever the catalog changes, now writes the table back whenever the config names magpie as its provider, at the top or in a profile, and has no table, whether Codex is connected or not. Check reports that state too. A config magpie can't parse is still only reported, never written to. A Connect that finds none of magpie's models because no provider or subscription has been added answers agent.NoModelsError, "Add a provider or subscription in magpie first, then connect Codex". /api answers it with code no_models and the agent's name, which app.js says through t() (en/zh/ja/de). docs/reference.md no longer says the table goes with a native model. TestCodexProviderWithoutTable (top and profile: Check says so, Sync writes the table) and TestConnectWithNoModels in internal/agent, TestAgentConnectNoModels in internal/gui, and agent-connect-no-models.test.cjs (WebKit, en/zh/ja/de: the toast in the reader's language, the switch back off, no scroll, no native dialog) are new and fail without the change; the latter's en case passes either way, as the server's message is English. Chromium wouldn't launch on this machine for this test or the existing agent-connect.test.cjs. TestCodexSyncAddsBaseURLToProvider now expects the table added to a hand-made provider that had none. go vet, go build (darwin, GOOS=linux nogui, GOOS=windows) and go test -tags nogui ./... under a temp HOME pass. In the first full run, internal/gui's TestProvidersAnswerWhileListsComeIn and internal/proc's TestUserPath failed under load; both passed alone and in the second full run.
|
||
|
yetone
|
2f135ed4d5 | plugin, gui, docs: Plugins says which plugins are providers and which are middleware, lists the community's ready-made middleware, and edits a middleware's options in its row (the owner) — the Plugins page still read as if every plugin were a subscription, and nothing showed what a middleware does or let you set its options without editing plugins.json. Every Discover card and Installed row now carries a Provider or Middleware chip (both for a plugin that is both), also for one that is off (isMiddleware/middlewareOnly from the server, read from its files); Discover splits into Subscriptions and Gateway middleware ("runs in magpie's gateway on what every agent sends and gets back, whichever provider serves it"), the latter from market entries with "kind": "middleware" and no providers or icon (the built-in market.json lists the five new @magpie-community/middleware-* packages: param-override, model-map, system-prompt, word-guard, think-tags, mostly New API's channel settings with the same JSON). A middleware row has Options: a JSON editor in the row, starting from the package's magpie.options example when none are set, which validates it is an object, saves (POST /api/plugins/options) for the next request, clears, and cancels with Esc. magpie plugin options takes a short name (model-map for @magpie-community/middleware-model-map; plugin.ShortName, also in SetOptions). en/zh/ja/de. Docs: usemagpie.ai/docs/plugins (en/zh/ja) gains Ready-made middleware and Options and the registry's kind; reference.md, both READMEs and docs/subsystems/gateway-middleware.md likewise. Tested with a real DeepSeek account and real Claude Code through magpie web --gateway in a sandbox HOME, with all five installed and options set by short name: a mapped model named back, max_tokens capped, a prompt appended for claude only, word-guard's 400 and param-override's 403 in the agent's shape, <think> stripped from Chat and Responses streams and a whole Anthropic reply, reasoning_content moved into the text; /api/plugins showed the kinds and the example. TestSetOptionsShortName is new; TestBuiltinMarket checks a middleware entry has no providers or icon and no other kind. plugin-middleware.test.cjs (Chromium and WebKit, en and zh: the chips, Discover's two sections, the options editor with its errors, no select, no scroll, no left border) fails without the change; the other plugin tests and click-scroll pass in WebKit (plugin-market's section name updated; plugin-move fails only under parallel load and passes alone). go vet, go build (darwin, GOOS=linux nogui, GOOS=windows) and go test -tags nogui ./... under a temp HOME pass. | ||
|
yetone
|
eebd0b4222 | plugin, gateway, gui: a plugin can be gateway middleware — onRequest, onEvent and onResponse run in magpie's gateway on what agents send and get back (moejs) — a plugin could only be a subscription provider, run in the Bun host, a process away from the gateway. A plugin may now declare middleware (package.json magpie.middleware, or a *.middleware.js / .mjs file), run in-process by moejs (pure-Go JS engine): compiled once, one runtime per request from a pool, so every hook of a request shares ctx.state. onRequest(body, ctx) sees the agent's body in its own API before routing; what it returns is the body the next middleware and the gateway get, undefined leaves the bytes as they were, ctx.reject(status, msg) answers with an error in the agent's API's shape. onEvent(ev, ctx) sees each SSE event's JSON (export const events = [...] filters by name; an object changes it, null drops it, undefined passes the bytes through untouched; data: [DONE] is no JSON and passes by). onResponse(body, ctx) sees a whole JSON reply, with ctx.status. ctx has protocol, model, stream, path, agent, the plugin's options and state. A hook that throws, returns a non-object or runs past its limit (250ms request/response, 50ms an event, 1s load; interrupted) leaves the request or reply as it was and is counted and logged (60 lines a minute); a compressed reply passes as-is. Files are reloaded within a second of a change. Only agents' requests run through it (serveAgent at the gateway's agent entry points and the Codex backend), never magpie's own titles, classifier or stand-ins; it sees bodies before redaction. A middleware-only package is skipped by the Bun host. The Plugins page marks a middleware with a chip, its hooks, calls and µs per call (JSON in and out counted), failures in red with the last error, and a load error. en/zh/ja/de; docs/reference.md and usemagpie.ai/docs/plugins#middleware (en/zh/ja) with an alias example. Tested with a real DeepSeek account through magpie web --gateway in a sandbox HOME: an alias middleware served "fast" and named it in message_start, a reject came back as 403 permission_error, a Chat stream uppercased; real Claude Code (sandbox CLAUDE_CONFIG_DIR) did Read, Bash and Glob tool turns through three middlewares with 0 failures: ≈1–1.6µs an event, 0.2–0.7ms an onRequest that parses and rewrites Claude Code's ≈80KB body. Real use found two bugs fixed here: [DONE] parsed as JSON (SyntaxError on every Chat stream) and stats leaving out the JSON time. internal/middleware tests (chain, undefined keeps bytes, reject, fail-open on throw/spin/string with the runtime reused, async hook, load errors, off and Bun skip, reload, split/CRLF/filtered/dropped stream events, [DONE] untouched, whole reply and gzip, 64 in parallel; BenchmarkEvent ≈0.9µs, 11 allocs) and TestMiddlewareThroughGateway (alias routed, events by protocol, redaction still upstream, reject in Anthropic's shape; fails without the change) are new; plugin-middleware.test.cjs (Chromium and WebKit, en and zh: chip, hooks and stats, failures with last error, broken and off, no left border) fails without it. The other plugin GUI tests and click-scroll pass in WebKit. go vet, go build (darwin, GOOS=linux nogui, GOOS=windows) and go test -tags nogui ./... under a temp HOME pass (internal/provider failed once under load and passes alone). | ||
|
Junjie Zhou
|
390db187c1 |
docs: introduce subsystem references and semantic change review (#889)
* docs: introduce subsystem references and semantic change review (#883) * docs: preserve Go caches and clean verification homes * docs: pin verification GOPATH and clean read-only files |
||
|
yetone
|
b9d20856ef | gateway, gui: a gateway key can be held to routing groups (Magic_zero on Discord) — a key's models menu on the Gateway page listed providers' models only, so a key couldn't be limited to the routing groups an agent was meant to use. The menu now lists the routing groups first, with Every routing group (group/*), and a key may keep group/<id>. A key that names a group may use it with every member in it, the next member too when one fails, but not those members asked for by name, a group it doesn't name, or a fallback outside the group; a group named inside one it doesn't name counts for its own members. A group the key doesn't name still passes only when it may use every member, as before. /v1/models and the Anthropic and Gemini lists show the key its groups. en/zh/ja/de; docs/reference.md. TestGatewayKeyModelsNameAGroup (group/both lists and serves only the group, falls to the next member, members by name and other groups refused; group/* every group; a nested named group; a member's own fallback outside the group refused) fails without the change; TestCallerKeyModelsRoutes lists the groups. gateway-key-groups.test.cjs (WebKit, en and zh: groups first after All models, Every routing group, a group picked sends group/coding, a held key's group ticked, no select, no scroll, no left border) fails without the change; gateway-key-models, gateway-key-limit and click-scroll pass in WebKit. go vet, go build (darwin, GOOS=linux nogui, GOOS=windows) and go test -tags nogui ./... under a temp HOME pass. | ||
|
yetone
|
1534382ff9 |
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.
|
||
|
maYandyetone
|
6fe8169502 |
gateway, agent: Codex draws with its native image tool through magpie (#870)
* fix(agent): give magpie's provider table the actor-authorization header
Codex offers its built-in image tool (image_gen.imagegen) — and the other
OpenAI-provider tools — only to a provider it reads as the OpenAI actor:
ModelProviderInfo::uses_openai_actor_authorization(), i.e. a provider that
does not require OpenAI auth but carries x-openai-actor-authorization.
magpie writes [model_providers.magpie] but carried neither signal, so a
Codex on magpie was never given the tool and could not draw through a
Codex backend such as sub2api's.
Write http_headers = { "x-openai-actor-authorization" = "magpie" } into
that table. magpie does not forward the header upstream: codexHeader
rejects anything naming "authorization".
Test: TestCodexMagpieProviderCarriesActorAuthorization.
* gateway/provider: let a Responses-only relay (Codex backend, sub2api) draw
A provider added as 'OpenAI Responses' only (what a Codex backend such as
sub2api speaks) has no chat base, so Drawers() returned nil before ever
looking at the vendor's list, draw() refused with 'can't draw', and
drawImages() posted to an empty base. The vendor's own /v1/models does list
its image models (sub2api serves gpt-image-2.5), and they are meant to be
picked in Settings → Images.
- Drawers: a Responses-only provider draws when it has any OpenAI-shaped
base, not only a chat one.
- draw: refuse only when neither Chat nor Responses is set.
- drawImages: fall back to the Responses base when there is no chat base.
- List: the add form's 'Fetch models' keeps the vendor's image models so
one can be picked while the provider is added.
Tests: TestResponsesOnlyProviderDraws, TestListOffersImageModels.
* fix: route Codex native images through its turn provider
---------
Co-authored-by: yetone <yetoneful@gmail.com>
|
||
|
yetone
|
46f03154ff |
gateway: a gateway key can be held to some models (#882, LCorleone) — a key could reach every model magpie serves. A key now keeps an optional list of models (caller-keys.json "models", none = every model, so older files read as before): <provider>/<model> or <provider>/*, matched against the provider that serves the call, so a bare model name is resolved first and OpenRouter's "anthropic/x" is not Anthropic's. Such a key sees only its models in /v1/models, /v1/models/{id} and the Anthropic (Claude Desktop) and Gemini lists, a routing group only when every member is its; asking for another, by id, bare name or through a group with a member it may not use, is refused before any provider is asked with a 403 in the API's own error shape (permission_error) that names the key and its models, logged as a rejected call like an over-limit key's 429; a fallback it may not use is skipped; embeddings, images and videos it names are held too. magpie's own calls for it (a web search, a picture described, Codex titles with the model Settings name) are marked in their context, not by a User-Agent a client could send, and go on. Set it with the new badge on the key's row in the Gateway page (the app's menu: All models, every model of a provider, each model; sent when the menu closes) or magpie gateway-key models <id> openai/gpt-5 anthropic/* (all takes it off); gateway-key list has a MODELS column. The app's menu, fitting neither below nor above its button, now goes on the roomier side and scrolls instead of running off the window. en/zh/ja/de. TestGatewayKeyModelsHoldAKey (lists, 403s by id, bare name and group, Anthropic shape, fallback skipped, magpie's own call, a free key) fails without the change; TestModelPatterns, TestKeyModelsKept, TestGatewayKeyModelsCLI, TestCallerKeyModelsRoutes pass; gateway-key-models.test.cjs (Chromium and WebKit, en and zh: no native select, menu inside a 420px window, picks sent on close, All models, no scroll, no left border, 560px fits) passes with gateway-connect-keys, gateway-key-limit, gateway-caller-keys and click-scroll. go vet, go build (darwin, GOOS=linux nogui, GOOS=windows) and go test -tags nogui ./... under a temp HOME pass.
|
||
|
yetone
|
9fb51c7742 |
docs: a new README, in English and Chinese, that shows what magpie does
The old README was the whole manual in one file. Someone who opened the repo saw a wall of config paths before seeing the app. The new one leads with the app: a hero screenshot, six highlights, then a section for each part (picking models, providers, routing groups and intent routing, subscriptions and plugins, usage, sharing, the library), with the site's light and dark screenshots in <picture> tags. A supported-agents list, a three-step quick start and a CLI sample follow. README.zh-CN.md is the same page in Chinese, with the Chinese screenshots where the site has them. The full manual moves, word for word, to docs/reference.md, with its two relative links fixed. Both READMEs link to it, so no detail is lost. |