yetone ddb6f806ac gui: the sessions warm-up hands its garbage back to the system when it ends, so a magpie just started doesn't read ~470 MB at rest for its first two minutes (H20 on Discord) ...

The warm-up reads every session file for the Sessions page and Usage › Requests. On a 13.5k-session history it allocates ~830 MB (QueryPage ~570, StatsFor ~260) to keep ~80 MB of indexes, and Go's scavenger returns the freed pages only over the next minutes. warmUp now calls debug.FreeOSMemory once its reads are done: one forced GC and scavenge, once, at start.

RSS of a linux nogui `magpie web` in Docker on a copy of a real config with those sessions mounted read-only, sampled every 15 s from start (with the dsh round change before it): 15 s 472 -> 197 MB, 30 s 475 -> 285, 60 s 417 -> 281, 2 min 337 -> 281, 3.5 min 266 -> 218, 12 min ~250 -> ~204. TestWarmUpReturnsItsGarbage fails without the FreeOSMemory call (10 of 10: 46-334 MB of freed heap still held, or the heap not yet collected) and passes 10 of 10 with it. go test -tags nogui ./internal/gui ./internal/sessions (Docker golang:1.26.8, temp HOME), go vet -tags nogui ./internal/gui for linux, windows and darwin, and gofmt -l pass. Not measured on macOS: a fresh build there hangs at exec behind syspolicyd today.

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

..

access

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

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

agent

agent: without dsh, the dsh round every 30 s doesn't build magpie's whole catalog for no patch list (H20 on Discord: magpie idles near 500 MB)

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

agentenv

agents: Qwen Code (qwen) as a managed agent (#1311)

2026-10-08 20:33:11 +08:00

appdir

appdir: a data folder beside magpie in the home folder, Downloads, Desktop or Documents is its portable data only when it holds magpie's files and the installed folder doesn't (or with .portable), so magpie.exe run from Downloads no longer writes into a user's own Downloads\data (tangle778 on X)

2026-10-07 18:13:01 +08:00

autostart

…

awake

settings: keep awake can keep the display on too (#975, Hu9956: magpie's keep-awake held the system up, but the screen still went black and locked, and their agents record the screen to check their work, which a locked screen stops) — Settings › General's "Keep awake while agents work" row now has three segments, Off / On / Screen on too, saved as keepAwake and the new keepAwakeDisplay (default off, so On and every existing settings.json behave as before). awake.Keep takes a Level (Off, System, Display) in place of a bool; a level changed while held releases and takes the hold anew. On a Mac the display level runs caffeinate -i -d -w <pid> (pmset -g assertions on a caffeinate of the same flags shows PreventUserIdleDisplaySleep beside PreventUserIdleSystemSleep); on Windows SetThreadExecutionState gets ES_DISPLAY_REQUIRED too; on Linux logind's idle inhibitor (systemd-inhibit --what=idle:sleep, unchanged) is all there is, and whether the screen stays on is up to the desktop. keepAwakeDisplay is this computer's own (KeepOwn) and goes in prefsKeep, so another setting's save keeps it. The row's line says the display stays on when it's chosen; it keeps its English in data-en, so a language change re-translates it. zh/ja/de strings added. No TUI or CLI has keep-awake, so none changed. TestKeepDisplay (taken once, taken anew with the display, not again at the same level, back to System, released at Off), TestCaffeinateArgs, TestExecutionState (GOOS=windows test build) and TestKeepAwakeKeptAndOwn cover it; go test ./internal/awake ./internal/settings ./internal/gui ./internal/gateway pass, -race -count=5 on awake. keep-awake.test.cjs now runs en/zh/ja/de at 900px and 440px in Chromium and WebKit (display posts keepAwake+keepAwakeDisplay true, the line changes, another setting's save keeps it, segments fit the row, On and Off clear it, no click moves the page): 32/32 twice; gui-ja, gui-de, i18n-keys and click-scroll pass. go vet (darwin, windows, linux), darwin, linux (nogui) and windows builds pass. Not tried with an agent recording the screen; the reporter is asked to confirm.

2026-10-06 15:33:28 +08:00

backup

backup: pin the #880 subscription sign-in policy with a test (#901)

2026-10-05 21:39:23 +08:00

budget

…

catalog

provider, catalog: a prompt cap above a model's window is held to the window (#1286) — a catalog row with limit.input over limit.context (opencode/hy3-free's 192K over 190K, Cloudflare AI Gateway's gpt-5 at 272K over 128K, venice/openai-gpt-52) was served past its window, to the gateway's /v1/models and to every agent compacting at it. The input limit still wins wherever it sits under the window (gpt-5's 272K of its 400K, a real prompt cap; OpenCode's own client compacts at input too), and a row naming only one number keeps it. TestPluginCatalogClampsInputAboveWindow and TestWindowClampsInputAboveContext fail without the change. go vet, go build -tags nogui and go test -tags nogui ./internal/provider ./internal/catalog under a temp HOME pass. (#1288)

2026-10-08 18:45:13 +08:00

claudebridge

…

codexcat

codexcat: a third-party entry for a model Codex has its own entry for (s2a/gpt-6-astra) says the same multi_agent_reasoning_effort, so Codex's Ultra sends xhigh for it as for OpenAI's gpt-6-astra instead of falling back to max (#1108)

2026-10-08 02:15:01 +08:00

davsync

davsync, gui: a WebDAV server whose HEAD says Content-Length: 0 no longer fails every shared usage day as "kept 0 of 6869 bytes", and a usage share that failed is its own red line under the sync status (#1259, mzcinf on 坚果云)

2026-10-08 14:52:11 +08:00

desktopdir

agent, library, sessions: a Claude Desktop installed as an MSIX package on Windows is found, wired, given MCP servers and skills, and its Cowork calls read, in the package's folders (Kilig on Discord, Windows 10 LTSC 21H2)

2026-10-08 12:47:48 +08:00

edit

edit: malformed JSON configs stay untouched when agents connect (#1242)

2026-10-08 11:52:20 +08:00

filememo

…

fonts

fonts: list upright styles before slanted faces at the same weight (#1030)

2026-10-06 21:15:19 +08:00

fx

…

gateway

gateway tests: the burst tests allow the moment a first word takes to reach magpie (TestCodexBackendBurstTellsNoSpeed red on macOS CI at 58f45d05: Millis 612, TTFT 13)

2026-10-08 21:20:46 +08:00

gui

gui: the sessions warm-up hands its garbage back to the system when it ends, so a magpie just started doesn't read ~470 MB at rest for its first two minutes (H20 on Discord)

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

imagemcp

library, imagemcp: magpie's own image server is given to agents in WSL, started through WSL's interop with the paths crossing over (#900, cjyrainbow) — on Windows the Library names magpie-image by this machine's binary ('D:\tools\Magpie\magpie-windows-amd64.exe' mcp image), and turning it on for "Codex · WSL Ubuntu" or "Claude Code · WSL Ubuntu" failed: a Windows program was refused for every agent in WSL. WSL's interop starts a Windows .exe from inside the distro, so magpie's own server (args mcp image, whatever its binary) is now written for an agent in WSL by the binary's path in the distro, asked of the distro itself (wslpath -u, so a custom automount root is followed; asked once in ten minutes; /mnt/<drive>/ when it can't be asked), with --wsl <distro>, --mount where the drives aren't under /mnt/, --home the distro's $HOME, and WSLENV naming the variables it is given (MAGPIE_ADDR), which a Windows program otherwise doesn't get. A distro whose interop is off (no WSLInterop in binfmt_misc) is told so: turn it on in /etc/wsl.conf. A user's own Windows program is still refused, as before: its paths and variables wouldn't cross over. A Linux magpie in the distro isn't looked for: the Windows one reaches the gateway at 127.0.0.1 and reads this machine's settings, the same version as the app, which a Linux one would need the gateway's address from inside WSL for. With --wsl, magpie mcp image opens the paths the agent gives (its roots, reference images, where to save, ~/) as the distro's — /home/me/x through \\wsl.localhost\<distro>\home\me\x (\\wsl$\ where that isn't), /mnt/c/x as C:\x — answers the saved paths as the distro's (/home/me/app/generated-images/…, /mnt/c/…), and with no project falls back to the distro's ~/Pictures/Magpie. Tested on the Windows 11 test box: in a WSL2 Ubuntu 24.04 distro the library's probe gave /mnt/c/…/magpie.exe and interop:on, and this build, started from the distro as the library writes it (the .exe's /mnt/c path, mcp image --wsl, MAGPIE_GATEWAY through WSLENV to a stand-in gateway in the distro), answered initialize and generate_image with a root of /home/yeton/m900proj: a relative path and an absolute reference image (sent as /v1/images/edits), ~/m900proj/home.png and /mnt/c/… were each saved there and answered as the distro's paths. TestWSLMagpieImage (the /mnt/d command, --wsl, WSLENV, nothing rewritten or asked again at the next sync, a custom mount, interop off as a problem) and TestLinuxHome in internal/library, TestWSLPaths in internal/imagemcp are new and fail without the change; TestWSLServers (npx.cmd still refused) passes. 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).

2026-10-05 20:09:34 +08:00

library

library: a skill an agent has of its own is removed from every agent that has it, from its row under "In your agents" (trash) or with d twice in the TUI, without bringing it into the library first (#1303, sxwedo)

2026-10-08 20:00:49 +08:00

mcpauth

…

middleware

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).

2026-10-05 19:14:31 +08:00

netproxy

netproxy: a host on the user's own network goes around the proxy (#982, jiz4oh: a Remote magpie's model list failed with "no model list: http://server…:3425/v1/models: 502 Bad Gateway", and Test with "no model to try", while curl with the key got the list) — the 502 had no body, which magpie's own errors always carry, and the other magpie logged nothing for the refresh: the request went to the proxy magpie takes from its settings, the environment or the system (Clash and the like), which couldn't reach the LAN name and answered 502. netproxy.Func now sends a request directly when the global proxy would take it and the host is on the user's network: a private, link-local, loopback or 100.64/10 (Tailscale) address, a .local name, or a name whose every address is one of those (looked up for at most 400ms, kept a minute; a name that doesn't resolve still goes through the proxy). A provider's own proxy is still taken as it is. Models, chat, count_tokens and the shared quota cards to a Remote magpie all go through Func (http.DefaultClient and the gateway's transport), so all are covered; so is any other provider on the LAN (an Ollama on a NAS). TestLANModelListNotThroughProxy (a proxy that answers 502 to everything, set in magpie, and a fake remote magpie on this computer's LAN address) fails without the change with the reporter's bare "502 Bad Gateway" and passes; TestLANGoesAroundTheProxy (IPs, LAN/Tailscale names, a vendor, a provider's own proxy) fails without it. Not tried on the reporter's network; they're asked to confirm. go test ./internal/netproxy/ ./internal/catalog/ ./internal/provider/ ./internal/gateway/ ./internal/update/ ./internal/usage/ pass; -race -count=5 on the new tests; go vet, darwin/linux(nogui)/windows builds pass.

2026-10-06 13:35:32 +08:00

omarchy

…

plugin

gateway tests: the keepalive tests count only the idle time a client waits through — the keepalive after the vendor's first words, and nothing after the reply's last event (#1163)

2026-10-08 10:28:06 +08:00

proc

proc: a CLI probe or agent run that is killed leaves nothing of itself running on Mac and Linux, even a launcher that keeps calling itself: its process group is signalled until it is empty, not once (#1278, JJ-Lin)

2026-10-08 18:18:15 +08:00

profile

…

provider

provider: moved Factory users get plugin 0.1.21, whose pi compaction summary no longer opens with the sentence Factory refuses (#1316, Eriice)

2026-10-08 21:15:25 +08:00

qoder

…

redact

cleanup: drop redact.Known and the quotaWire type — nothing calls either (deadcode -test -tags nogui, git grep). vet on darwin, linux, windows; redact and provider tests pass.

2026-10-06 06:07:02 +08:00

sessions

sessions: a Codex archived copy rewritten at the same size in the clock tick of its last comparison is compared again, not taken from the cache, on Windows too (#1299, wizzy-yang)

2026-10-08 19:04:18 +08:00

settings

stats: the day's event says which agents, providers and models magpie is used with, by magpie's own ids (a provider of the user's own, and its models, only "custom"), with how many of each and of routing groups: one "magpie uses" event per id in the same PostHog batch, so unique users break down by agent, provider and model. Settings → Privacy → Share the agents, providers and models I use turns it off (on by default; gone while Count me as a user is off); no names, URLs, accounts, keys or usage. go test ./internal/stats (payload, off switch, labels), the Privacy switch in Chromium and WebKit (en, zh), go test -tags nogui ./... in a temp HOME, go vet, GOOS=linux/windows builds pass; read against the real config: 9 agents, 24 providers, 25 groups in 0.75 s

2026-10-08 19:26:13 +08:00

shortcut

…

source

…

stats

stats: the day's event no longer names an omp profile or a model the user named; an omp profile goes as omp, and on a key's provider a model id models.dev doesn't list (an Ollama model, a fine-tune with the user's organisation in it) goes as <provider>/other

2026-10-08 20:24:57 +08:00

steady

…

testenv

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

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

tui

library: a skill an agent has of its own is removed from every agent that has it, from its row under "In your agents" (trash) or with d twice in the TUI, without bringing it into the library first (#1303, sxwedo)

2026-10-08 20:00:49 +08:00

update

tests: a fake program is a file macOS has already let run (testenv.Program), so a fake's first start no longer eats a test's wait under load

2026-10-07 03:00:47 +08:00

upstream

upstream: the vendors' own status pages say when their API is down (#971, emo172: an Anthropic or OpenAI outage looked like a sign-in or quota problem) — a provider that calls Anthropic's, OpenAI's or Moonshot's API (by its base URL's host: api.anthropic.com, which the Claude subscription calls too; api.openai.com and chatgpt.com, Codex's; api.moonshot.cn/.ai) carries "API outage" (red), "API degraded" or "API maintenance" beside its name on its Providers row and its Usage card while the vendor's page says so; its title names the parts and the open incidents, and a click opens the incident (or the page), not the row. internal/upstream reads each page's Statuspage-style summary.json (status.claude.com; status.openai.com, incident.io's; status.moonshot.cn), checked by hand on 2026-10-06, and only the API's own parts (Claude API and Claude Code, not claude.ai; Chat Completions, Responses, Codex, Codex CLI, not "Codex in ChatGPT Desktop", which was degraded that day); an incident naming no parts (OpenAI's) counts only while those parts are affected. Pages are read only when the Providers or Usage page asks (GET /api/upstream), at most once in five minutes, never on a request's way; a page that fails, isn't JSON or no longer lists the API's parts is unknown and marks nothing. A relay serving the same models is never marked. DeepSeek's page (Flashduty) has nothing readable and is only known for its link; OpenRouter, xAI, Mistral and z.ai have no page read. The gateway's failure messages, TUI, CLI and tray aren't changed. zh/ja/de added. upstream_test (fake pages from the real summaries: API down, claude.ai down isn't the API, Claude Code degraded, OpenAI's app isn't the API, 503/HTML/changed page unknown, read once in Fresh and Of never waits, hosts; -race -count=5) and gui's TestUpstreamRoute pass; upstream-status (Anthropic down: its provider and the Claude subscription marked, relay/OpenAI/unread Moonshot not, click opens the incident not the row, all well marks nothing; 900 and 440px, the badge whole, the name giving way) passes in Chromium and WebKit, en and zh, and fails 8/8 without the app.js change. i18n-keys, gui-ja, gui-de, click-scroll, account-return, account-models, usage-keys-fold, deprecated-subscriptions and add-sheet pass; go vet, go test ./internal/gui/, linux/windows/nogui builds pass.

2026-10-06 12:36:05 +08:00

usage

usage: a subscription card's window says what the whole window holds, "Whole ≈ N tokens · ≈ $X", reckoned from what magpie routed through the account since the window began over the share used, at API list prices (Chiao on Discord)

2026-10-08 20:53:03 +08:00

wslrun

agent, wslrun, sessions, gui: Settings → General has Detect agents in WSL; off, magpie asks wsl.exe nothing and shows no WSL agents or sessions (#1264)

2026-10-08 16:57:39 +08:00

zed

…