okooooooo/magpie
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
e6dd5d20bbf1cf67da98a1cc8d506b9064c2cdab
magpie/docs/subsystems
T
History
yetone 76321e3b42 gateway: a lone provider's Claude or GPT reasoning streams as it comes, not held for a refusal no one else could answer (iTianbao on X: 请加一个开关，让思考实时透传; through a relay Claude Code showed the thinking only all at once with the text, Codex none until then) — holdWriter held Claude's, GPT's and Gemini's reasoning (refusesAfterThinking, up to holdThinking) on every candidate, so a refusal after it could go to the next one (#248), but a refusal on the last candidate is never asked again (the !last checks in serve), so there it only delayed the thinking. On the last candidate Claude's and GPT's reasoning is now shown at once (thinkingShown), and a refusal after it reaches the agent as the vendor's own stop; Gemini's stays held there, for a reply that only reasoned to be asked again (#667, TestGeminiEmptyRepliesAskedAgain). A group with members after it still holds as before. Before: on a slow fake relay (4 thoughts 300ms apart, then text) every relay shape (Messages, Chat with reasoning_content and reasoning, Responses) for claude-sonnet-4-5 and gpt-5.1 gave Claude Code's thinking_delta and Codex's reasoning_summary_text.delta all at ~1.2–1.5s with the text; after, 0/300/600/900ms. TestThinkingStreamsWithNoOneElse (Messages, Chat for Claude and GPT, Responses; each asked from /v1/messages and /v1/responses) fails without the change in every case and passes; TestHeldThinkingKeepsTheAgentAlive's nobody-left case now expects the thinking and Claude's refusal rather than a held error. -race -count=5 on TestThinking*, TestRefusal*, TestHeld*, TestGeminiEmpty*; go test -tags nogui ./internal/gateway, go vet, gofmt -l, linux and windows (nogui) builds pass. Not tried with the reporter's relay: whether it sends GPT's reasoning at all (OpenAI's Chat API doesn't) is unknown, and no switch was added. docs/subsystems/gateway-routing.md says it.
2026-10-06 19:34:24 +08:00
..
agent-wiring.md
agent, gui: an agent connected by its config to an address where nothing answers is told, not shown connected (#1013, cjyrainbow: Codex Desktop's WSL environment reads Windows' ~/.codex/config.toml, whose openai_base_url and [model_providers.magpie].base_url the reporter pointed at Windows as WSL sees it, forwarded to 127.0.0.1:3425 by a portproxy of their own; after a reboot the portproxy listened no more and the Agents page still said Codex was connected) — Drift looked only at the config, which was right. Now an agent pointed at an address off loopback (this machine's Codex at an address the user kept, #816, through Agent.reach; every WSL twin under NAT, at Windows as the distro sees it, through Agent.Gateway) has that address tried from here (reach.go: GET /v1/models, any HTTP status an answer, 2 s timeout, in the background, at most every 20 s per address, never waited for), and one that doesn't answer while the gateway answers on loopback is a new drift, "unreachable", with Addr and the advice in Detail: under WSL (or on Windows) magpie with Settings › Share on local network on, or the user's netsh interface portproxy, which may need setting up again after a restart; Windows' firewall allowing the port for the WSL network; on Windows 11, networkingMode=mirrored; elsewhere, the forward to start again or gateway.URL() to point at. An answer not had yet, and a gateway down on loopback too, are no drift. The config is never changed for it, except where the address is one a WSL distro reached Windows at before (distro.Was, the last 4 kept in wsl.json as a re-probe finds Gateway changed) and the distro reaches Windows at another now: Drift's Move names that one, and Reapply moves the config there (Agent.move; Codex's codexMoveGateway rewrites openai_base_url and magpie's own provider's base_url, only where they begin with the old address). An address no distro was seen at is the user's own and is never offered a move. In the GUI the row's line says "{agent} is set up, but nothing answers at the address it reaches magpie by" in red with the advice as its tooltip, and its pill is "How to fix" (an i, not the reapply arrow), which opens the advice in a dialog (too long for the status line; it wraps and can be copied) and sets nothing — or "Use <address>" (the existing "Use {url}" string) when there is a Move, which reapplies; two new t() strings with zh, ja and de. The probe runs from Windows, not from inside WSL, so a firewall keeping WSL out isn't seen; the advice names it. TestKeptAddressNotAnswering (the reporter's case: Codex at 172.28.96.1, unreachable with the address and loopback in the detail; no drift once it answers, none with the gateway down too), TestKeptAddressProbeNeverWaitedFor, TestKeptAddressMovedWithWSL (Move from a Was address, Reapply rewrites both URLs, Check empty and no drift after; a 10.0.0.7 address is told but never moved) and TestWSLAgentAddressNotAnswering (Codex in a NAT distro told, with Share on local network, portproxy and firewall; a mirrored one never probed) fail without the Drift change and pass; TestLoopbackNotProbed, TestReachProbe (httptest: a 401 is an answer, a closed port none) and TestWSLWas pass. TestMain stubs reachProbe so no test dials out. -race -count=10 on them; go test -tags nogui ./internal/... under a temp HOME, go vet (darwin, windows), gofmt -l, linux and windows (nogui) builds pass. agent-unreachable.test.cjs (the window at 560px and the tray panel at 440px: the red line and tooltip, How to fix's dialog posting nothing, Use <address> posting the reapply, no sideways scroll) fails on main and passes on Chromium and WebKit in en, zh, ja and de; agent-connect, agent-layout, agent-field-names, aside-native, gui-de, gui-ja and i18n-keys pass on both. Not tried on a real WSL NAT setup (the Windows test box didn't answer ssh). docs/subsystems/agent-wiring.md says it.
2026-10-06 19:17:55 +08:00
claude-subscription-bridge.md
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.
2026-10-05 22:56:30 +08:00
gateway-middleware.md
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.
2026-10-05 20:50:09 +08:00
gateway-routing.md
gateway: a lone provider's Claude or GPT reasoning streams as it comes, not held for a refusal no one else could answer (iTianbao on X: 请加一个开关，让思考实时透传; through a relay Claude Code showed the thinking only all at once with the text, Codex none until then) — holdWriter held Claude's, GPT's and Gemini's reasoning (refusesAfterThinking, up to holdThinking) on every candidate, so a refusal after it could go to the next one (#248), but a refusal on the last candidate is never asked again (the !last checks in serve), so there it only delayed the thinking. On the last candidate Claude's and GPT's reasoning is now shown at once (thinkingShown), and a refusal after it reaches the agent as the vendor's own stop; Gemini's stays held there, for a reply that only reasoned to be asked again (#667, TestGeminiEmptyRepliesAskedAgain). A group with members after it still holds as before. Before: on a slow fake relay (4 thoughts 300ms apart, then text) every relay shape (Messages, Chat with reasoning_content and reasoning, Responses) for claude-sonnet-4-5 and gpt-5.1 gave Claude Code's thinking_delta and Codex's reasoning_summary_text.delta all at ~1.2–1.5s with the text; after, 0/300/600/900ms. TestThinkingStreamsWithNoOneElse (Messages, Chat for Claude and GPT, Responses; each asked from /v1/messages and /v1/responses) fails without the change in every case and passes; TestHeldThinkingKeepsTheAgentAlive's nobody-left case now expects the thinking and Claude's refusal rather than a held error. -race -count=5 on TestThinking*, TestRefusal*, TestHeld*, TestGeminiEmpty*; go test -tags nogui ./internal/gateway, go vet, gofmt -l, linux and windows (nogui) builds pass. Not tried with the reporter's relay: whether it sends GPT's reasoning at all (OpenAI's Chat API doesn't) is unknown, and no switch was added. docs/subsystems/gateway-routing.md says it.
2026-10-06 19:34:24 +08:00
gui-shell.md
gui: let users choose installed interface and code fonts (#1007)
2026-10-06 19:32:56 +08:00
library.md
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).
2026-10-06 02:24:53 +08:00
provider-plugins.md
plugin, provider: a plugin can press its vendor's daily check-in itself (auth.checkin), and magpie runs it as its own check-ins (Lemon on Discord #feedback: provider 每日签到的方法能放到插件里面去做吗; ARNO earlier asked for Qoder's) — the check-ins magpie had (WorkBuddy, Trae CN, MiniMax Code, Qoder) are each written in magpie against the vendor's endpoint, even for a subscription that moved to its plugin, so a plugin author had no way to give their provider one. A plugin's auth hook may now have checkin(getAuth, provider) beside usage: the host lists the provider with checkin: true (plugin.Provider.Checkin) and answers checkin({provider, account}) (plugin.AccountCheckin), refreshing the account as usage does, with {outcome, credit, streak, message}; outcome is claimed, done, ineligible, inactive, captcha or failed, and a throw or an outcome outside these is failed with the reason. internal/provider/plugin_checkin.go runs these through checkin.go's checkiner, as the built-ins are: each signed-in account in use once a Beijing day (first look 2 minutes after start, then every 30), a failure asked again after wbCheckinRetry, every other outcome settled for the day, results kept in plugin-checkin.json by provider|account; a failure is recorded as failed and resets nothing. captcha is new (CheckinCaptcha): the vendor wants a captcha, which magpie never solves, so it is said as "check in in its own app", not as a failure, and not asked again that day. The results mark the account's Usage card (checkinBy "plugin:<provider>", WithCheckins), so the card's check-in row, its Auto check-in and Check in now work for it (POST /api/settings/plugin-checkin {provider, on}, POST /api/usage/plugin-checkin {provider}); Settings → Usage gains a Plugins tab, shown while such a plugin is signed in, a Daily check-in row per provider with Off/On and how each account went; magpie accounts checkin and c on the TUI's Usage page include them (the TUI's "no account" line names check-in plugins). The switch (settings.PluginCheckins, by provider) is off by default; for WorkBuddy, Trae CN, MiniMax Code and Qoder it follows that vendor's existing switch until set on its own, and magpie's own check-in through the plugin's fetch leaves a provider whose plugin checks in to it (pluginChecksIn), so no account is checked in twice. The Settings page's save carries PluginCheckins over (TestSettingsSaveKeepsWhatItDoesNotSend's fixture names it). No plugin declares the hook yet; Qoder's check-in stays magpie's own here. TestPluginCheckinRunsAsTheBuiltinsDo (the fake plugin with FAKE_CHECKIN, five accounts answering claimed, done, captcha, a throw and an unknown outcome: off presses nothing; on, each outcome kept with its vendor; a minute on nothing pressed again; past the retry only the two failures; the next day all five; PluginCheckins and the cards marked; another provider's press asks none) and TestPluginCheckinTakesOverTheVendors (a qoder plugin without the hook leaves magpie's Qoder check-in its account, with it none; PluginCheckinOn's fallbacks) pass -race -count=10, and the latter fails with pluginChecksIn stubbed false; TestTUIChecksPluginsIn passes -race -count=20. plugin-checkin.test.cjs (the card's row with the captcha said, Auto check-in posting {provider, on}, no page move; the Settings Plugins tab at 440px with the row fitting, no sideways scroll, On posting) passes on Chromium and WebKit in en, zh, ja and de; usage-checkin, i18n-keys, gui-ja, gui-de and settings-* pass. go test -tags nogui ./internal/..., go vet, gofmt -l, linux (nogui) and windows builds pass. Not tried with a real plugin or account: no published plugin has the hook yet. docs/subsystems/provider-plugins.md (the hook's contract) and docs/reference.md say it.
2026-10-06 18:40:45 +08:00
providers-accounts.md
gateway, provider, gui: a Sub2API key given 5h/1d/7d limits is weighed and rested by its own windows, like an account (#1004)
2026-10-06 18:57:47 +08:00
README.md
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)
2026-10-06 02:17:14 +08:00

README.md

Subsystem design references

These pages describe current responsibilities, runtime paths, state, and contracts. Start with the subsystem relevant to your task, then follow its source links to verify the implementation you change.

Subsystem Reference
Built-in subscriptions moving to plugins Provider and plugin ownership
Plugins that run on the gateway's requests and replies Gateway middleware
Claude subscription turns across Claude Code runs Claude subscription bridge
How the gateway picks a provider, key or account, and falls back Gateway routing and fallback
Connecting an agent's config to the gateway, drift, disconnect, WSL twins Agent wiring
Providers, keys, subscription accounts, refresh and allowance Providers and accounts
Instructions, MCP servers, skills and RTK written into agents Library
Tray, panel, window, magpie web and the page's JSON API GUI app shell

A subsystem can span several packages or repositories. Its reference describes the behavior those parts provide together; it does not need to list every function.

Maintain a reference

Update the owning reference in the same PR when a change alters a documented responsibility, interface, state transition, runtime path, compatibility rule, or failure behavior. An internal refactor that preserves these contracts does not require a prose change.

Keep each fact in one reference and link to it from agent instructions or other pages. Link to source files and named symbols rather than copying implementation details that change frequently. Explain field meanings and constraints that signatures alone do not express.

For a new reference, include the responsibilities and boundaries, source of truth, main runtime paths, state transitions, important constraints, and existing verification commands. Include failure and compatibility behavior where relevant. Document current behavior separately from proposed changes; the proposal belongs in its issue or PR.

Describe a PR's semantic changes

For each affected subsystem, explain the observable change with its trigger and before/after behavior. Include changes to interfaces, state, compatibility, and failure behavior when relevant. Link the affected reference, implementation, and verification evidence. State when a refactor preserves the documented behavior.

For example, a change to plugin adoption should explain which migration state and account condition trigger it, which implementation handles requests before and after adoption, and which test exercises that transition.

This is an author-provided explanation that a reviewer verifies against the diff and surrounding code. It is not an automatically proven compatibility verdict.

Review a change

  1. Identify the affected subsystem and the actual runtime path, including plugin or built-in ownership.
  2. Compare the claimed before/after behavior with the base and head implementation. Trace relevant callers and state transitions beyond the changed lines.
  3. Check that changed contracts appear in the owning reference and that source links still resolve.
  4. Check that the cited tests or runtime evidence exercise the claimed behavior. Report checks that were not run.

A documentation update alone does not prove the implementation. Existing tests and runtime evidence remain necessary for behavior changes.

Reference in new issue View Git Blame Copy Permalink