c06a550b73680289d5a94de7a412356d4040297d
76
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 yetone
|
05683637d5 |
plugins: the Bun the plugin host runs on is kept as magpie-bun, so a proxy app's PROCESS-NAME rule can route the requests plugins (Cursor and the other moved subscriptions) make (#1048)
magpie downloads its own Bun into ~/.cache/magpie/bun/<version>/. It is now written there as magpie-bun (magpie-bun.exe on Windows), and a Bun downloaded before is renamed in place the first time it is looked for, so nothing is downloaded again and no second copy takes disk. The host, bun add and bun update all run it, so all of their traffic carries the one name. A $MAGPIE_BUN the user set is run as it is. Verified: TestBunDownloadedAsMagpieBun, TestBunDownloadedBeforeTakesTheName and TestHostRunsAsMagpieBun fail without the change (the Bun is .../bun, the host runs .../bun). TestHostRunsAsMagpieBun starts the real host on a copy of Bun 1.4.2 and `ps -o comm=` names it magpie-bun on macOS. On the Windows box the three tests pass with the Windows build of Bun 1.4.2, a running bun.exe renames to magpie-bun.exe, and Get-Process/Win32_Process name it magpie-bun. Linux not run here (CI's ubuntu job runs the test with Bun on PATH). go test -tags nogui ./... green; -race -count=10 on the new tests green. |
||
|
yetone
|
de2c84ace7 |
gateway: a Responses relay that turns away reasoning with nothing sealed in it, naming only the input, is asked once more without it, and isn't sent it again for that model (#1044: Codex's /compact through Anyrouter failed with 400 invalid_request_error param=input on old conversations)
Codex hands back reasoning items with no encrypted_content (an rs_ id and a summary, as magpie's translated replies give it). #1008 left them out only for OpenAI's API and Azure OpenAI. A relay in front of OpenAI turns them away the same way but with its own message ("bad response status code 400", param "input"), so the compaction, which is relayed as it is, failed. They are not left out for every other upstream: a DeepSeek model behind a Responses relay wants its reasoning back (#388), and magpie's own translator reads the summary as thinking. passthrough now, on a 400 to a Responses request whose error names the input (refusesInput: param input / input[…], or an item named by id), asks once more without the bare reasoning (withoutBareReasoning), sealed reasoning and every other item kept; once that works the provider and model are remembered (bareReasoningRefused) and later requests go without it at once. Any other 400 goes back as it came. TestBareReasoningLeftOutWhereRefused (the reporter's item kinds: message, function_call(_output), custom_tool_call(_output), two bare reasoning items and a sealed one; the relay's 400 word for word) fails without the gateway.go change for both the compaction and a relayed turn (400 back to Codex) and passes. TestBareReasoningKeptWhereTaken and TestBareReasoningKeptOverAnotherRefusal guard the upstreams that take it and other 400s; TestAzureCompactionWithoutMagpiesReasoning (OpenAI/Azure unchanged) still passes. -race -count=5 on these, TestCodexCompact* and TestImageTool*; go test -tags nogui ./internal/gateway ./internal/provider, go vet ./internal/..., gofmt, linux and windows (nogui) builds pass. Not tried against Anyrouter itself (no account); the 400 is from the issue's capture. |
||
|
yetone
|
698da36f31 |
gateway, providers, gui: a model on this computer or the local network can be set to get requests unmasked by Settings' redaction (lc on Discord: 本地模型可以不脱敏)
The provider editor has a Redaction row, "Send requests unmasked", while
every address of the provider is on this computer or the local network
(localhost, *.local, a loopback or private IP): Ollama, LM Studio, a vLLM
box. Ticked (provider.Unredacted; CLI `magpie provider set <id>
unmasked=yes`), a request whose provider and fallbacks, or whose routing
group's models, all skip redaction (provider.SkipsRedaction) goes to them
as the agent wrote it; anything that may reach another provider stays
masked for all of them. An address edited to a vendor's masks it again; a
signed-in account, a plugin's provider and another magpie never skip. The
log and recent calls keep the masked body. count_tokens and embeddings
follow the same rule.
It is a per-provider choice, not automatic for local addresses, because
a local address isn't a local model: a relay run locally (new-api,
CLIProxyAPI) or Ollama's cloud models pass the request on to a vendor.
Verified: TestLocalUnredactedProviderGetsTheRequestWhole (set, unset,
fallback to a vendor, fallback to another local one, a group of it alone,
a group with a vendor; chat and count_tokens) and TestLocalUnredactedEmbeddings
fail without the gateway change ("sent whole false, want true: … my key is
{{API_KEY_…}}"; count_tokens alone: "counted whole false"); TestSkipsRedaction;
TestProviderSaveKeepsUnredacted fails without the preset save line.
provider-unmasked.test.cjs (Chromium+WebKit, en/zh, 900 and 440 wide) 32/32,
3 of 4 fail on the old app.js; gui-ja, gui-de, i18n-keys, provider-search
and the other provider editor suites pass. go test -race on gateway,
provider, redact, gui; -race -count=10 on the new tests; go vet,
GOOS=linux/windows builds. Real: a sandbox gateway in front of the local
Ollama (llama3 8B) through a logging proxy: unset, Ollama was sent
{{API_KEY_…}}; with unmasked=yes it was sent the key as written, and
answered both times.
|
||
|
yetone
|
92469ee9f9 |
library, gui: a check for updates lists the skills a repository added beside the library's skills from it, to Add or Ignore (Raven on Discord)
Raven: "check for updates" only updated skills already in the library; when
dontbesilent2025/dbskill or mattpocock/skills adds a skill, magpie never said.
CheckSkills now asks GitHub's git trees API once per repo@ref (ETag-cached, a
304 is free) and only when a skill folder under the installed skills' common
folder (newBase) is neither in the library nor already offered does findNew
fetch the tarball for names and descriptions. library.json's seenSkills keeps,
per repo@ref, the paths the install picker showed and the ones set aside, so
an offered skill is offered once. The Skills page shows them under "Also in
their repositories" with Add (to the agents that have the repo's other skills)
and Ignore, plus Add all / Ignore all (/api/library/skills/{add-new,ignore-new}).
Verified: TestCheckSkillsFindsNewOnes (fake repo: nothing offered after
install, no tarball on a second check; two added skills offered, a nested one
and a .wip one not; Add installs with the repo's agents; Ignore keeps it out
on the next check via 304; remove clears) fails without the change (no
NewSkills / findNew) and passes -race -count=10; TestNewBase. A real run in a
sandbox HOME against GitHub: tdd from mattpocock/skills/skills/engineering
offered its 19 siblings; dbs from dbskill offered nothing (the picker showed
all), 33 with seenSkills wiped, and Add installed dbs-action. GUI:
skill-new-in-repo.test.cjs (Chromium+WebKit, 860/440px, en+zh) fails on
main's library.js and passes; gui-ja, gui-de, click-scroll, library-items,
every-skill, pick-skills, import/remove-all-skills, skill-groups,
skill-repo-groups, github-token, library-all pass. -race on library, gui,
tui; gofmt, vet, darwin/linux/windows builds.
|
||
|
yetone
|
a7e7fe2b0f |
library: switching a group of skills on or off no longer reads every copy every agent has (#1031, mintonight: 开关一整个技能组时很卡，要10多秒才能完成)
The page already sends one request for a group (agents-some), but its one
change ran a sync that, for every skill given as a copy (every WSL agent,
Windows without the right to link, agents set to copies), hashed the copy
and the library's skill twice, in every agent, on every change, and the
page's read hashed the copies once more. Over a WSL distro's share that is
every file of every skill read through 9P each click.
A copy's mark now keeps the hash of what was copied (markCopy). A copy
whose mark says the library skill's current hash, with nothing in it newer
than the mark, is current without its files being read (copyIsFresh);
takeEdits' walk of a copy is not done a second time in the same sync, and
each library skill is hashed once per change (libHash). Copies with an old
mark, or edited since, are hashed as before. Claude Desktop's copies and
project copies use the same check.
Measured in a sandbox (55 skills x 31 files, copies for 10 agents, a
5-skill group switched on for an 11th): the change went from 1.54s to
0.31s and the page's read from 0.66s to 0.25s on a local SSD; the copies
not touched are no longer read at all, which is the cost over WSL.
TestSyncDoesNotReadUnchangedCopies fails without the change ("codex's
copy of pdf was read and made again"): an unreadable file in an unchanged
copy is left alone now. TestCopyFreshByMark checks a changed library skill
is still copied again, an old mark without a hash still works, and an edit
in a copy is still taken. go test -race ./internal/library ./internal/gui
pass, the new tests pass -race -count=10; vet, gofmt, darwin/linux/windows
builds pass. Not run on Windows or WSL.
|
||
|
yetone
|
14af0f100b |
provider, plugins: a plugin's browser sign-in finishes from the address the browser ended on, for magpie on a server or in Docker (Chicring)
The built-in sign-ins that come back to a port on this machine (Codex,
ChatGPT API, Devin, Kiro, Zed, Gemini, Antigravity) already took the
pasted address. Their plugins didn't: a subscription moved onto its plugin
(Devin, Kiro, Zed) or a plugin's own browser sign-in (Trae) showed only
"the account shows up here as soon as you're done", and a browser on
another computer than magpie's ended on a page that won't load with no way
to finish.
Now a plugin's "auto" sign-in whose page names a port on this machine to
come back to (redirect_uri, auth_callback_url, callback on localhost, or
Zed's native_app_port: loopbackPorts) sets pasteCallback, so the GUI shows
the same Callback URL field as the built-ins, and `magpie plugin login` /
`magpie accounts add` ask for it too. SubmitSignInCallback opens the pasted
address on 127.0.0.1 at that port, never through a proxy, so the plugin's
own listener finishes the sign-in as it would for the browser; an address
on another port or host is refused, a page that sends the browser on to a
page that comes back to the same port (Kiro's AWS sign-in) becomes the next
page to open. Command Code's page posts its key from script, which leaves
no address to paste, so it keeps offering the plugin's API key way.
Verified: TestPluginSignInTakesAPastedCallback (fake plugin with a loopback
sign-in, $FAKE_LOOPBACK) fails without the wiring in pluginBegin ("a
sign-in that comes back to a port here takes no pasted address:
{... PasteCallback:false ...}") and passes with it, -race -count=10;
TestLoopbackPorts covers the community plugins' page addresses.
go test -race ./internal/provider ./internal/plugin and the root package's
Plugin|Login|SignIn tests pass; vet, gofmt, darwin/linux nogui/windows
builds pass. With the real community Devin, Zed and Kiro plugins in a
sandbox HOME, each sign-in offered the field and a pasted address reached
the plugin's listener and the vendor (bogus code refused by Devin 401, Zed
"couldn't be decrypted", Kiro 400). signin-paste-plugin.test.cjs (new),
signin-callback and signin-paste-codex pass in Chromium and WebKit, en and
zh, at 360px; no new strings. Not tried: a real successful sign-in from a
browser on another computer.
|
||
|
Zhizhen He
|
dfc66030e8 |
provider: keep saved credentials when reading or backing them up fails (#1034)
Follow up #965: keepUnreadLogins still ignored read and backup failures,
so a new sign-in could replace credentials that had not been recovered.
Return those errors and stop writeLogins before replacing the original.
A missing logins.json can still be created, and successful backups keep
the existing behavior. Document the save failure contract.
TestUnreadLoginsWriteErrorsKeepCredentials fails on the latest base for
both faults with "original credentials overwritten" and passes with the
fix. The unread-logins tests also pass under -race -count=20.
On
|
||
|
yetone
|
dcbae2ef98 |
library, gui: the MCP servers page has the skills page's Select, Turn all on, Turn all off and Remove all, under one "In the library" heading (#1027, emo172)
The servers page had only By agent and the order, each with its own "In the library" heading, so with both the heading showed twice. Turning every server on or off, or removing them all, took one chip or one row at a time. The page now has one heading (lib-serverhead, which wraps when narrow) holding the order, Select, Turn all on, Turn all off, By agent and Remove all, as the skills page does. The skills page's helpers now serve both pages rather than being copied. picking names the page ("skills" or "servers"). pickingFor, pickRow, pickBar and groupChips(kind) are shared, and so are everyButtons, confirmEveryOff and everyOf, which replace everySkillButtons and everySkill. removeEveryButton, confirmRemoveEvery and removeEvery replace removeEverySkillButton. The skills page says and does what it did before.
- Turn all on and Turn all off post every agent shown to servers/agents-all (EveryServerAgents, now serversAgents(nil, …)). A hidden agent is left alone. Turn all on is greyed once every server is on for every agent that can reach it. Turn all off asks first, in the page.
- Select puts a box on each row. A row's click ticks it rather than opening the server. The bar's chips post the servers picked to the new servers/agents-some (SomeServersAgents), which gives an agent only the ones it can reach (mcpFile.supports) and leaves unnamed servers and agents as they are. An agent that can reach none of the picks has its chip greyed, with the reason.
- Remove all asks first. It says which agents lose the servers, the projects they are taken from, the sign-ins forgotten, and that the agents' own servers stay. It then posts every name to the new servers/remove-all (RemoveServers). This is one change that takes each server out as RemoveServer does: out of the library, its projects and its icon (removeServer, now shared by both), then out of every agent through syncMCP, which takes only what Applied says magpie wrote, and then forgets its sign-in. A name the library hasn't is listed in Unremoved, and the rest go all the same.
- The pick bar wraps, so its chips and Done fit at 440px in ja and de.
TestRemoveServers checks a server the user put in Claude Code's file and Codex's own "docs" of a library server's name: both stay, while fs, docs and neon leave the library, both agents and the project's .mcp.json, and the project's own "team" stays. neon's sign-in is gone, "nope" is reported, and an empty list or one with only "nope" errors. TestSomeServersAgents checks that Codex gets fs but not the SSE web, that git stays untouched, that a call naming no servers or no agents errors, and that a call naming an unknown server writes nothing. Both pass with -race -count=10, alongside TestEveryServerAgents and TestRemoveServer*.
library-servers-bulk.test.cjs passes on Chromium and WebKit in en, zh, ja and de at 440px. It checks one heading with every button, Turn all on's post without the hidden Copilot CLI, Turn all off's Cancel posting nothing and Confirm keeping Copilot CLI's, the pick bar's codex chip posting agents-some for the two picked and its greyed state for web alone, the All box, Done, and Remove all's lines, Cancel and post. It also checks for no sideways scroll and that each control clicked stays where it was on the screen. The fake check answers every server, since an unchecked one is checked again at each drawing. It fails without the change and passes 6 runs beside pick-skills, every-skill and gui-ja at --test-concurrency=4. by-agent, pick-skills, every-skill, remove-all-skills, group-*, library-*, mcp-signin, project-servers, skill-*, i18n-keys, gui-ja and gui-de pass. skill-how's WebKit case and click-scroll's "Live and a day" fail the same on the unchanged origin/main when run beside each other, and pass alone. go test -tags nogui ./internal/..., go vet, gofmt -l, and the linux (nogui) and windows builds pass. Not tried in the real app. docs/subsystems/library.md says it.
|
||
|
yetone
|
33e4f165aa |
docs: how magpie picks an account — the steps a request's accounts go through, what Make first counts under each routing, Smart's and Weekly pace's real rules, rests after running out, gateway vs. on its own, and how often an allowance is read (#1032, Cyb3rN8)
docs/reference.md gets a section "How magpie picks an account" after Routing
groups; docs/subsystems/gateway-routing.md links it and notes the two
points users most often misread. Docs only; no behavior changes.
Every claim in the issue was checked against origin/main (
|
||
|
tsuixl
|
29f4909262 |
fonts: list upright styles before slanted faces at the same weight (#1030)
Follow up on the Menlo style ordering noted in PR #1007. Compare normal, italic and oblique explicitly after weight, retaining the existing width and name tie-breakers. The Menlo regression fails before the change with Italic, Regular, Bold Italic, Bold, and passes with Regular, Italic, Bold, Bold Italic. Group/tie-break tests, fresh Windows native discovery, focused nogui GUI/font tests, go vet and Windows/Linux nogui builds pass. |
||
|
yetone
|
dd027bc433 | sessions: a Claude Code workflow's agents are read as their session's calls (ksinverse on X: 发现Claude的用量和会话不太准，codex就非常好。是不是sub-agents没有被统计进去？默认开ultracode) — Claude Code writes a workflow's (ultracode) agents a folder deeper than other subagents, <session>/subagents/workflows/<run>/agent-*.jsonl beside the run's journal.jsonl, and ccFiles read only <session>/subagents/*.jsonl, so with ultracode on every workflow agent's calls and tokens were missing from Usage, the Requests page and the session's totals. ccFiles now reads each run's agent-*.jsonl too (the journal isn't a transcript and stays out), and sessionOfPath gives them their session, so they count as the session's like any subagent's; Claude Desktop's and Qoder's readers, which share ccFiles, follow. TestCallsWorkflowAgents (a session, a workflow agent's file and a journal with a line that reads as a call) fails without the change (1 call, the agent's missing) and passes. On this machine's real ~/.claude (read only), 34 workflow-agent calls of one session were unread and are now that session's. go test ./internal/sessions, -race -count=10 on TestCalls*/Subagent*/Trace*, go vet (darwin, windows), gofmt -l, linux and windows (nogui) builds pass. Not tried against the reporter's own transcripts. docs/reference.md says it. | ||
|
yetone
|
a334fe091c | gateway: a request a proxy or tunnel on this computer forwards to loopback is answered as one from another machine, and needs the gateway key (#1022, znjhahaha: asked for a Cloudflare Tunnel in magpie, with the gateway key checked for requests through it) — local() was the request's address alone, so cloudflared, ngrok, Tailscale serve or funnel, frp's HTTP proxy, or a Caddy or nginx here, all reaching 127.0.0.1:3425 for clients anywhere, were taken for this computer's agents: whoever had the tunnel's address used the user's subscriptions with any token, read /v1/magpie/quotas (the accounts and their balances) and the remote cards, and their usage was counted as local, all without sharing on. reference.md said a proxy here had to sign its clients in itself; a quick tunnel signs in nobody. A request on loopback carrying a forwarding header (Forwarded, X-Forwarded-For, X-Real-IP, Cf-Connecting-IP, True-Client-IP, Tailscale-User-Login), which no agent sends, is now proxied, and local() is false for it, so every check built on local() takes it as from the network: lanGuard refuses it while magpie isn't shared, saying it came through a proxy or tunnel and that Settings → Share on local network and a gateway key let it in; shared, it needs an enabled gateway key and is then sharedWith, as a LAN client is, for the model APIs, quotas, remote cards, concurrency, session route and MCP sign-ins; the Omarchy theme and the Codex title link stay this machine's only, and its usage is no longer marked local. A gateway MAGPIE_ADDR opens to the network stays open to a tunnel as to anyone; one MAGPIE_ADDR keeps on loopback is closed to it. MAGPIE_TRUST_PROXY=1 says a proxy here signs its clients in itself and keeps what it forwards local, as before (listed in agentenv_test's notAnAgent). A tunnel forwarding bare TCP (frp tcp, ssh -R, socat) adds no header and can't be told from an agent: reference.md says to point one at the LAN address with sharing on. Running cloudflared from magpie with a pasted Tunnel Token is not done here: magpie would have to download or run a program it doesn't ship; reference.md says how to serve magpie through a Cloudflare Tunnel today. TestProxiedLoopbackNeedsTheKey (from 127.0.0.1 with cloudflared's, ngrok's, nginx's, RFC 7239's, Akamai's and Tailscale serve's headers: refused unshared, 401 shared without a key, with magpie's token or a wrong key, let in with the key under its identity, a disabled key refused; an agent on loopback let in with any token; MAGPIE_TRUST_PROXY; MAGPIE_ADDR on loopback and open) and TestProxiedLoopbackRoutes (quotas, quotas history, models, Omarchy and /mcp through a tunnel, unshared and shared, with and without the key) fail on main (200 for every tunnel unshared) and pass -race -count=10 with TestLANGuard, TestQuotasOverLAN, TestManagedLANGuard and TestExplicitOpenGatewayAcceptsAllRemoteTokens; go test -race -tags nogui ./internal/gateway (579 s, under -timeout 30m) and go test -tags nogui ./internal/... under a temp HOME pass; go vet (darwin, windows), gofmt -l, linux and windows (nogui) builds pass. No GUI change. Not tried with a real cloudflared (not installed here); its Cf-Connecting-IP and X-Forwarded-For are what Cloudflare documents it sends. | ||
|
yetone
|
555f570660 | gateway, provider: the Routing page says what a lone key or account has left, and a key bought as a plan (Kimi Code, GLM Coding Plan, MiniMax, OpenCode Go, Command Code) is weighed by its plan's windows (#1016, gphysign: Kimi Code (China) with one key on, Smart routing; the card said only "Kimi Code (China) 只启用了一个 Key，无需选择。" while /v1/magpie/quotas had its 5 hours 49 used, 51 left and its 7 days 45 used) — two gaps. weighRouted returned before reading anyone's allowance when there was one candidate, so a lone key or a lone subscription account was never known in the trace, and the Routing page, which shows a bar and "{n} used · renews in {d}" for a known row, had nothing to show; every single-account subscription said "what's left not known yet" the same way. And KeyAllowance read only a sub2api key's limits, so a key whose plan the Usage page reads (planQuotaSourceOf: Kimi Code, GLM Coding Plan and Z.ai, MiniMax Coding Plan, OpenCode Go, Command Code) was never known to routing, with one key or several. weighRouted now reads what each candidate has left before returning a lone one (one alone is still weighed against nobody). readsKeyWindows takes a plan key too; keyWindows reads it through planKeyWindows (planWindows, with Zhipu's team quota behind a key that has none of its own, as PlanQuotas does), and PlanQuotas' own read of a card is noted for routing at once (noteKeyAllowance), so the Usage page and routing never ask twice; the card kept on disk seeds it after a restart (keyCardTag keys a plan card as plan:, a sub2api one as balance:). A key at such a vendor that turns out to be pay-as-you-go, with no windows, is asked again every 30 minutes (keyNoWindowsAge), not every minute it is used. So, beyond the issue: several plan keys on one provider are now weighed by their windows under Smart, usage and pace, and a plan key the vendor refuses as out of quota rests until its window renews and comes back once read short of full, as a sub2api key does. affine no longer says a lone key or account all but used up "moved" its conversation: there is nobody to move to (at > 0). The GUI needed no change. TestLoneOneTellsWhatItHasLeft (a lone Kimi key known at 49% with both renews, the week first; a lone Codex account known; a plain DeepSeek key not), TestLoneSpentKeyKeepsItsConversation (fails with the at > 0 guard taken out), TestPlanKeyAllowance (the windows read behind the request, asked once; DeepSeek and Moonshot keys never asked), TestPlanKeyAllowanceFromItsCard (PlanQuotas' read known at once without a second ask; after a restart with the vendor down, the card on disk stands in and a failed read keeps it) and TestPayAsYouGoKeyAskedSeldom (a GLM pay-as-you-go key asked once, not two minutes on, again 31 minutes on) all fail without the change and pass -race -count=20 (provider) / -count=10 (gateway). routing-key-windows.test.cjs gains a lone Kimi Code key at 1100px and 440px (the one-key story, the row's bar at 49%, its provider row "49% used · renews in …" fitting, no sideways scroll) and passes in full on Chromium and WebKit in en, zh, ja and de; routing-quota-left and panel-routing pass. go test -tags nogui ./internal/..., go test -race on ./internal/provider and ./internal/gateway in full, go vet, gofmt -l, darwin, linux and windows (nogui) builds pass. Not tried with a real Kimi Code key. StepFun's Step Plan is read through a sign-in, not the key, so it isn't one of these. docs/subsystems/gateway-routing.md, providers-accounts.md and docs/reference.md say it. | ||
|
TryWorld
|
fde0c38c56 |
fix(gateway): a refusal that arrives once the reply began rests nobody (#1015)
A member whose reply had begun and whose vendor's safety filter then
refused the turn — Chat's code content_filter, Anthropic's stop_reason
refusal, Responses' bio_policy — was booked as a vendor failure
(Fail other) and rested with a backoff, so later requests skipped a
healthy account. The same refusal, said before any of the reply was, is
booked failRefused and rests nobody, and the request is handed to the
next member (#248). Only the timing differed: a refusal is about the
request's content, not about the account (
|
||
|
yetone
|
e6dd5d20bb | usage, gateway, gui: a reply that reasoned is timed by its answer, from its first text, not by all its output from its first token (tony on Discord #general: Usage › Requests read "gpt-6.1-sol 163 token/秒 · 8,036 个请求 · 首字 14 秒" and asked whether subagents were added up) — speed was every output token over the time after the first content (text, reasoning or a tool call). Output counts the reasoning, and a model whose reasoning is hidden (OpenAI's encrypted reasoning, a summary sent when it is done, Claude's omitted thinking) writes it before the stream shows anything, inside the TTFT; so a 2,000-token think and a 200-token answer over the 1.5 s after the first token read 2,200 in 1.5 s, 1,467 tok/s. Concurrency was not the cause: the aggregate is Σ tokens over Σ per-request windows, so subagents running at once never add up. In the owner's own usage.jsonl codex/gpt-6-luna turns read up to 600 tok/s (out 496, reasoning 224, 11,055 ms, ttft 10,228) and its aggregate 133; it is 80 now. usage.DecodeOf is the one rule: a reply with reasoning counts out − reasoning over ms − firstText, one that reasoned and wrote only tool calls tells no speed, one without reasoning is timed from its TTFT as before; DecodeWindow's burst cut (#731) still applies. Record.Decode feeds summarize, the ledger's Totals and its timeline Parts; a route keeps its reply's reasoning (Route.Reasoning, from gateway.go and codex_backend.go), and routing.js's decodeOf/speedOf times its rows, the story and a session's average by it (an older route takes its served usage's reasoning); app.js's ledDecode does the Usage page's rows, whose tooltip says the reasoning left out, and the Output speed help says the rule, in en, zh, ja and de. History is read the same way, as it keeps the reasoning and the first text. Routing never ranks by speed. TestReasoningReplyTimedByItsAnswer (the 2200/2000 turn, a summary 10 ms before the text, a concurrent subagent, tool calls only, reasoning over output, no reasoning, not streamed: 1,200 tokens in 11 s through summarize, addRow, LedgerSeries and Decode) fails without the change and passes -race -count=10; TestUsageKeepsTimeToFirstToken now has its paced replies report reasoning and checks the route keeps it. reasoning-speed.test.cjs (Routing rows 133, 100, none and 100, the story never 1,467, the session 105; the Usage rows, tooltip and KPI the same; no sideways scroll) passes on Chromium and WebKit in en, zh, ja and de, and fails against the old assets (1467 tok/s); routing-request-metrics, routing-burst-speed, usage-speed, usage-ledger-detail, i18n-keys, gui-ja, gui-de, ledger-hscroll and click-scroll pass on both. go test -race -tags nogui ./internal/... under a temp HOME passes but internal/proc's TestUserPath ("the login shell's PATH never came"), which failed under the full run's load, passes 3/3 alone and is not touched here; go vet, gofmt -l, linux and windows (nogui) builds pass. Not tried with tony's data. docs/reference.md says how output speed is counted. | ||
|
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. | ||
|
tsuixl
|
bd33e575f1 |
gui: let users choose installed interface and code fonts (#1007)
* gui: choose installed interface and code fonts and styles Discover installed styles through DirectWrite, CoreText and Fontconfig. Keep choices per computer, apply them before paint and notify both desktop webviews after saving; defaults retain platform and Omarchy fallbacks. Verified seven focused Go tests, including real Windows discovery (90 families, 276 styles), 14 font browser cases in Chromium/WebKit, 68 settings/zoom/Omarchy/web cases, go vet, Windows amd64/arm64 and Linux nogui builds. Against the original assets, the new UI test fails with Settings must offer an interface font picker (0 != 1). Full Windows suites have separately reproduced upstream failures; macOS/Linux native discovery is covered by the added CI step. * gui: retain bundled Mac fonts and variable style precision Only filter an undownloaded CoreText face when it is explicitly downloadable; bundled fonts are installed without being downloaded. Use resolved font names when descriptors omit them. Preserve fractional weights and nonnegative CSS widths for named variable styles. * gui: restore the authored font cascade when returning to defaults Apply family-only trait overrides only while a custom face is active. The browser regression catches code under a bold parent becoming 700 instead of its original 400. Keep the compatibility shim first, and apply boot fonts before visible content. * gui: keep font picker review separate from CI integration Leave the native test sources and manual verification command with the feature. Move the added workflow step to a follow-up so the font picker can take the normal review path requested on PR #1007. |
||
|
yetone
|
490d2ea362 | gui: the tray panel's Allowances tab hides subscriptions and moves them, from an Arrange at its foot (H20 on Discord: "菜单栏的详情页能不能选择某些不显示，有点额度并不想看到或者可以调整顺序，目前的还不行") — the panel's tab already followed the Usage page's order (usageOrder, byUsageOrder), but it could be set only by dragging a card's logo on the window's Usage page, which nothing in the panel said, and there was no way to leave a subscription out of the panel at all. The tab's foot now has Arrange, and "{n} hidden" beside it when some are: Arrange lists a row a subscription (balances too) in the shared order, its logo the handle (a drag, or Alt+arrows; the grip by it on hover only, as on the Usage page) and a Hide/Show pill, under a note that hiding is the panel's only and the order is the Usage page's too; Done draws the cards again. What's hidden is kept in magpie's settings (settings.PanelUsageHidden, panelUsageHidden), not the browser: routing, caps, the Usage page and the menu bar's cells still have it, and a menu bar cell for a hidden subscription still opens its card (panelPeek) until the panel is put away or the tab left. POST /api/usage/arrange takes order and panelHidden and changes only the one it is sent (both were whole-order before; an order alone still works), and the Settings save keeps panelUsageHidden as it does usageOrder. Saves draw at once and are put back with the error if they fail; no click moves the page (the view's scroll is kept across the redraw); no native select, no left-border stripe. Which allowances the menu bar shows beside its icon stays Settings' pick (trayUsages). New t() strings have zh, ja and de. TestUsageArrangePanelHidden (each field set and cleared on its own, a Settings save between) passes -race -count=20, TestSettingsSaveKeepsWhatItDoesNotSend's fixture names the field. panel-arrange.test.cjs (440px: the hidden card left out and counted, Arrange keeping the reader's scroll, the rows and note, the hover-only grip, no stripe, no sideways overflow, Show/Hide posting panelHidden without a scroll and a failed save put back, Alt+arrow and a drag posting the order, Done's cards in it, a menu bar cell opening a hidden card until the panel hides, the Usage page keeping the hidden card) passes on Chromium and WebKit in en, zh, ja and de; click-scroll, gui-ja, gui-de, i18n-keys, panel-fold, panel-usage, quota-*, routing-quota-left, tray-cell-click, tray-inuse, tray-logos, tray-usages, usage-accounts(-fold), usage-arrange, usage-fold, usage-quota-head, usage-card-refresh, usage-stale-answer, usage-remote-cards, api-key-usage, claude-usage-asked and usage-checkin pass on both. go test -tags nogui ./internal/... under a temp HOME, go vet, gofmt -l, linux (nogui) and windows builds pass. Not tried in the real tray panel on a Mac. docs/reference.md and docs/subsystems/gui-shell.md say it. | ||
|
yetone
|
588e51ea4c | 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. | ||
|
yetone
|
c5a54bc74b | agent: VSCodium's magpie group is written for the provider its installed Copilot Chat declares, OpenAI Compatible (customoai) on the Marketplace's 0.48.1 (#1014, xybio: VSCodium's Chat picker showed only Auto) — VSCodium has no Copilot Chat of its own, and the last Marketplace Copilot Chat it can install, 0.48.1, declares no Custom Endpoint provider (its contributes.languageModelChatProviders: copilot, copilotcli, claude-code, anthropic, xai, gemini, openrouter, openai, ollama, customoai, azure), so the customendpoint group magpie wrote in chatLanguageModels.json was never read. magpie now reads the package.json of the github.copilot-chat installed under ~/.vscode-oss/extensions (vscodeChatOf: the one extensions.json lists, else the highest github.copilot-chat-<version> folder not in .obsolete) and writes customendpoint when it is declared, customoai when only that is: each model's window as maxInputTokens beside maxOutputTokens (0.48.1 adds them up), and the token as x-api-key, since 0.48.1 drops an Authorization in requestHeaders and its apiKey has to be a ${input:} secret; the gateway already takes a key from x-api-key, past an empty Authorization, so Usage still counts VSCodium. No extension found, or a package.json that can't be read, keeps customendpoint as before; one declaring neither is said in Notice and Check. Writing the group removes magpie's group for the other provider in the default's and each profile's file, and Disconnect removes both; the user's own groups, under either provider, stay. Sync (at magpie's start and on catalog changes) rewrites a group written for the other provider, and Check reports it until then. VS Code and Insiders, whose chat is built in, keep customendpoint unchanged. The Notice says 0.48.1 registers its providers only while signed in to GitHub with a personal Copilot plan (its BYOK registration is gated on the Copilot token's individual/BYOK flag). TestVSCodiumCopilotChatOpenAICompatible (the real 0.48.1 provider list installed in a temp ~/.vscode-oss: Connect writes customoai with x-api-key magpie-vscodium and no Authorization or contextWindow, the user's groups kept, Check empty; a Custom Endpoint group an older magpie wrote is flagged and rewritten by Sync; a Copilot Chat declaring customendpoint switches it back; one declaring neither is reported; Disconnect removes both) and TestVSCodeChatInstalledWithoutExtensionsJSON (folder scan, .obsolete, unreadable package.json) fail on main, which writes customendpoint, and pass; -race -count=10 on the VS Code tests, go test -tags nogui ./internal/..., go vet, gofmt -l, linux and windows (nogui) builds pass. No GUI change. Not tried with a real VSCodium. docs/subsystems/agent-wiring.md and docs/reference.md say it. | ||
|
forever
|
b0a96cbbd7 |
gateway, provider, gui: a Sub2API key given 5h/1d/7d limits is weighed and rested by its own windows, like an account (#1004)
* gateway: a Sub2API key out of its 5h/1d/7d limit ("…限额已用完") rests as out of quota, not a 1-minute rate limit
Sub2API refuses a key that has spent the 5-hour, day or 7-day limit its
owner gave it with 429 "api key 7天限额已用完" (or 日限额, 5小时限额),
typed rate_limit_exceeded. It matched rateWords and not plannedWords
("限额" is not "额度"), so failure() said rate: the key rested a minute,
was tried again, refused again, and sank, for the days its 7-day window
had left. plannedWords now has 限额已用完, so it is failQuota.
The relay's other refusals keep their classes, fixed by the test: the
pool out of accounts (v0.1.149's 503 "No available accounts": other;
later versions' 429 "All available accounts are currently
rate-limited": rate), its upstream's rate limit (rate), the key's own
total quota API_KEY_QUOTA_EXHAUSTED (quota) and the wallet's 403
INSUFFICIENT_BALANCE (credit).
Verified: TestSub2APIKeyLimitIsQuota, with Sub2API v0.1.149's message
bodies. Without the change it fails: "429 {…api key 7天限额已用完…}:
rate, want quota", and the same for 日限额 and 5小时限额.
* provider: a Sub2API key's /v1/usage shows its 5 hours / 1 day / 7 days windows instead of nothing at "remaining"
A Sub2API key its owner gave a 5-hour, day or 7-day spending limit
answers /v1/usage in quota_limited mode with rate_limits — each
window's limit, used and reset_at in dollars — and, without a total
quota of its own, no "remaining". With the Balance URL set to it, the
key's card said `nothing at "remaining" in the reply`.
readSub2APIKeyLimits reads rate_limits into the windows the cards
already name 5 hours, 1 day and 7 days, in USD. A window not started
(used 0, no reset_at) is taken to renew a span from now; a window with
a limit of 0 is none. The card shows them, beside a balance field the
user wrote; with none, Check balance and `magpie provider show` give
what the fullest window has left. A wallet key's reply is unchanged.
KeyAllowance gives routing the same windows, per provider and key: read
behind the request, never waited for, at most once a minute (once for
any number of asks at a time); a failed read keeps the last; after a
restart it is seeded from the card's last reading in quotas.json;
StaleKeyAllowance has it read again at the next ask. ForgetBalances (a
key or Balance URL changed) has every key read again, a read begun
before dropped, the last reading standing until then. Only keys whose
Balance URL is a Sub2API /v1/usage are asked: any other key, and every
account, costs nothing here.
Verified with real bytes of a limited key's reply, its key removed
(testdata/sub2api_usage_key_limits*.json): TestReadSub2APIKeyLimits,
TestSub2APIKeyLimitsOnItsCard, TestKeyAllowance*. Each fails without
its part, e.g. the card without the windows: `Error:nothing at
"remaining" in the reply`; KeyAllowance waiting for the read: "waited
30.0s"; asking every time: "asked 11 times"; a failed read asked again
at once: "asked 22 times after failing"; not seeded: "seeded = [],
false"; any key asked: "asked /api/usage/token"; ForgetBalances
dropping what was read: "after ForgetBalances, and a read begun before
it: []"; leaving a read under way loading: "the key's windows were
never read"; a stale-generation read landing: it replaced 95%; a limit
of 0 taken: "a day's limit of 0 = [{… Used:100 …}]"; Balance from the
first window only: "$300.00" for $80 left.
* gateway, gui: keys whose windows magpie reads are weighed and rested by them, like accounts
Smart, least-used and pace routing weighed only subscriptions by their
windows: weighRouted skipped every key (c.p.Account == nil), so a
Sub2API key beside Codex accounts in a group went by its place in the
order, and, refused for its 7-day limit, rested a quarter of an hour at
a time while the window had days to run.
A key whose own windows magpie reads (KeyAllowance: a Sub2API key given
a 5h/1d/7d limit, its Balance URL /v1/usage) is now weighed as an
account is: fine, low (90%) or spent (98%), the one renewing soonest
first, in a provider and in a group alike, and its trace row carries
them. Out of quota it rests till the window it filled renews, by
candidate.full; when its windows as last read aren't full it rests
quotaRest, and either way they are read again (staleKeyAllowance).
Every other failure of a key backs off as before, never to the window:
the relay out of accounts for everyone (503/429) says nothing of the
key's own spend. capHeld and pooled stay accounts' only. Keys magpie
reads no windows of are ordered exactly as before.
The Routing page tells such a key as it does an account: its row's bar,
used share and renewal, why it went first by its allowance, "Every key
and account here is at 90% or more", and the Smart header. A key not
read yet beside one read is told as weighed with it, not "keys go in
their order" or by its tokens. New strings in en, zh, ja and de.
Other users of the relay draining its accounts don't show in a key's
windows, which count only its spend: they show as the pool's 503/429,
which back off and fall over to the next key, account or fallback.
Verified: TestKeysWeighedByTheirWindows, TestGroupWeighsKeyWindows,
TestKeyOutOfItsWindowRestsUntilReset, TestKeyPoolErrorDoesNotRestForWindow;
and routing-key-windows.test.cjs in Chromium and WebKit (en/zh/ja/de).
Without the change they fail: "smart: kw#a kw#b kw#c"; "the key renewing
first: codex sub2api"; "full: rests 14m59.99s by quota"; "read again:
[]"; backing off to the window: "pool empty: rests 71h59m59.99s by
window (other)"; and on the page "relay-a goes first: keys go in their
order, those that suit the request first." where all are at 90% or
more, or a key not read yet beside one read.
* gateway, provider: a Sub2API key out of its limit is back once its windows read short of full, not only when the window renews
A key refused for its 5h/1d/7d limit rests till the window it filled
renews: days, for the week. Its windows are read again behind the next
requests (a minute apart) and by its card, but nothing lifted the rest
when they came back short of full, so the owner raising the key's limit
in the relay's panel, or resetting its usage, left the key out till the
week turned, though the relay would take it at once. Accounts have this
already: a Codex reset spent tells OnRenewed, and the gateway lifts the
account's rests (renewed).
A key's reading, routing's or its card's, now tells OnRenewed the same
way, as agent "" and the key's KeyAllowanceID, when a window it was full
in (Allowance.Full at SpentShareOf its routing, as candidate.full counts
it) is full no more, or full till sooner. Its first reading, a failed
read, or one that finds it fuller tells nothing. The gateway notes the
key's KeyAllowanceID on its rest out of quota only, so renewed lifts
that rest and no other: the relay out of accounts for everyone (503)
still backs off, and another key still out of its week stays out.
Where nothing weighs the key by its windows, nothing read them again
either: an ordered group weighs each member's keys alone, so a member
with one key, like a provider with one key, never asks for them. After
the one read its 429 starts, the key sat out its week on that reading.
restingOf, which plans a resting key behind the rest, now asks for the
windows of a key resting out of them (agent "" and a user on its rest),
so the next request planned past a minute reads them, behind it, and a
reading short of full brings the key back there too. No card is read
for it, and a key resting for any other reason asks nothing.
Verified: TestKeyAllowanceRenewed (provider) and
TestKeyBackOnceItsWindowIsNotFull (gateway, end to end through the key
cards' reads and restAfter), each failing with a piece of the change
undone: never telling, "its week's limit raised to $1,000: told []" and
"a, its limit raised: still rests by window till …"; telling on any
change, "its first reading, out of its week: told [/sub2api#…]"; a
failed read telling, "a read that failed: told [… …]"; the card not
telling, "its usage reset, read on its card: told [/sub2api#…]"; the
rest not noted, "a, its limit raised: still rests by window"; every
rest of a key noted, "c, the relay out of accounts: …, false"; renewed
not matching the key, "b, still out of its week: …, false". And
TestRestingKeyReadAgainInAnOrderedGroup (gateway: an ordered group, its
first member one key on a fake /v1/usage, no card read after the 429),
failing without restingOf's ask: "its limit raised: still rests by
window till …, its windows read 1 times".
Tried on a real Sub2API v0.1.149 relay, in a sandbox HOME, its key's 7d
limit lowered under its spend for the test and then restored, with
magpie serve on a group ordered: the key, then a local stand-in. The
key answered 429 "api key 7天限额已用完"; it rested by window till its
7d reset, 2026-10-13 00:00 +08:00, and the stand-in served. Planned
again a minute later, still over, it still rested. With the limit back
at $800, the next request was planned with it resting, the stand-in
serving, and read its windows; the one after went to the key, 200.
|
||
|
yetone
|
87487c5ef0 | 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. | ||
|
yetone
|
b56bfb5a94 | gateway: an upstream that answers 200 with a web page, with nothing at all, or with JSON that isn't, has failed as a 502 does, so a group asks its next member (#1012, cth123456: Codex on group/medium, agentrouter/deepseek-v4-flash now and then answered 200 text/html; the log said status=200 done=true in=0 out=0 served=null, codex/gpt-6-luna was never asked, and Codex failed with "stream disconnected before completion: stream closed before response.completed") — the candidate loop judged a try by its status alone, and holdWriter passes a 200 that is neither text/event-stream nor application/json straight to the agent, so the page went to Codex as the reply. notAnAPIReply now reads every 2xx (but 204) an upstream gives, in forwardOnce (every relayed and translated request, every API, plugins included) and in the built-in clients' own requests (the ChatGPT backend's /responses, Kiro, Zed, Qoder, Devin, Cursor, Command Code): a text/html reply, a body that begins as a web page whatever its Content-Type, an empty body, or one sent as JSON that doesn't begin with { or [ is turned into the 502 it stands for, with a JSON error saying what came back ("answered 200 OK with a web page (text/html), not an API reply: “Just a moment...”", the firewall hint for a block page). It then fails over, rests a minute and is logged as any 502 before the reply begins does; a provider with nobody after it hands the agent that 502 rather than the page. Only the first bytes are peeked, which a stream waits for anyway; a read that fails is left to the reader, a compressed body and anything else as it came. TestNotAnAPIReplyFailsOver (Chat, Responses and Messages, streamed and not, a member answering a Cloudflare page as text/html, as JSON and as SSE, an empty body as JSON and as SSE, and plain text as JSON; the next member must answer and the log name why) fails without the change in all 36 cases (the page relayed to the agent, or b never asked, or no reason logged) and passes; TestNotAnAPIReplyAlone (a 502 with the reason, logged 502) and TestCodexBackendWebPage (the ChatGPT backend's page reached Codex as a 200) fail without it and pass; TestAPIReplyUntouched keeps JSON after whitespace, SSE with and without a Content-Type, gzip, XML, a 204 and a 404 as they came. -race -count=10 on them; go test -tags nogui ./internal/gateway ./internal/provider, go vet (darwin, windows), gofmt -l, linux and windows (nogui) builds pass. Not tried with the reporter's relay (agentrouter) itself; the page is a Cloudflare challenge's, as the issue has only its Content-Type. docs/subsystems/gateway-routing.md says it. | ||
|
yetone
|
a87dc1ff2b | gateway: a WebSocket upgrade on /v1/responses is answered 426 "magpie relays Responses over HTTP only", not 404 (#1005, Clarence12138) — Pi's Responses WebSocket extension opens GET /v1/responses with Upgrade: websocket, and only POST was routed there, so the catch-all's 404 ("magpie serves …") read as a broken gateway and the extension retried five times a session before falling back to SSE. GET /v1/responses and /responses now tell an upgrade 426 with the reason and the way that works (POST, streamed as SSE) — the answer a client falls back to HTTP on at once, as the Codex backend path already gives (TestCodexWebSocketUpgradeRequired) — and a plain GET 405 with Allow: POST. Relaying Responses over a WebSocket itself is not done here (a long-lived connection whose model is named per response.create, outside the per-request routing, failover, key limits and usage the gateway has). TestResponsesWebSocketUpgradeRequired fails without the change (404) and passes; go test ./internal/gateway, go vet (darwin, windows), gofmt -l and the linux build pass. Not tried with Pi's extension itself. docs/reference.md and gateway-routing.md say it. | ||
|
yetone
|
6ba82d2f07 | gateway: reasoning magpie made isn't relayed to Azure OpenAI or OpenAI's API, and a summary request refused for an item not found is asked again as text (#1008, zhouxiong100: Codex on an Azure OpenAI deployment failed every compaction with "Azure OpenAI: Item with id 'rs_18dbe693b3dce4800000003c' not found", Reconnecting 5/5, store=true by a middleware no help) — Codex offers web search on every turn, so its turns on Azure went out translated, and the translated replies gave Codex reasoning items magpie made: rs_ and newID (the reporter's id is one, a UnixNano in hex and a counter), a summary and nothing sealed. Codex hands them back on every turn. buildResponses replays no reasoning to Azure, so the turns worked; Codex's compaction offers no tools, so it isn't translated but relayed as it is, and Azure, with store false, looked rs_… up among stored items, found none and answered 400 for the whole request. codexCompact asked again as text only on a 404 (#866), so the 400 went back to Codex. passthrough now drops reasoning with no encrypted_content from a Responses request to OpenAI's API or Azure OpenAI unless store is true (withoutBareReasoning): both look such an item up and can't have it, its summary being the model's notes no model reads back; their own sealed reasoning still goes, and every other host gets the request as before (a relay may read the summary for a vendor that wants reasoning back). The same holds for any turn relayed as it is, Codex's with web search off for one. codexCompact's fallback also takes a 400 naming an item not found (itemNotFound: unreadableItem and "not found"), as a relay in front of either passes on; any other 400 still goes back as it came, and the local summary names the status it got. TestAzureCompactionWithoutMagpiesReasoning (the Azure preset at a fake /openai/v1/responses answering a storeless request with a bare reasoning item Azure's 400 word for word; the compaction and a relayed turn, each asking Azure once with the sealed reasoning kept and magpie's dropped) fails without the passthrough change (the turn 400 with the reporter's exact message, the compaction asking twice) and passes; TestCodexCompactItemNotFoundAsksAgainAsText fails without the codexCompact change (400 to Codex) and passes; TestCodexCompactOther400Stays guards other 400s. -race -count=10 on them, TestCodexCompact* and TestAzureRoutes. go test -tags nogui ./internal/gateway ./internal/provider, go vet, gofmt -l, linux and windows (nogui) builds pass. Not tried with a real Azure OpenAI resource (none on this machine); the 400's text is from the reporter's screenshot and issue. docs/subsystems/gateway-routing.md says it. | ||
|
yetone
|
5361a2178e | agent, gateway: Cursor Private Inference's row has an effort, which magpie's gateway asks its requests for (#1003, gjf7) — other agents' rows pick a reasoning effort that magpie writes into their config, but Cursor Private Inference reads only its base URL and key from the environment, and its app offers no Reasoning control for most of magpie's models, so there was no way to set one short of a routing group with a member fixed at a level, which the reporter used as a workaround. Its row now has an effort field like the others': the default (as Cursor asks) first, then every level the models it lists have (cursorLocalEfforts: their levels in MemberEfforts order, low/medium/high where a model reasons with levels unknown, none at all when nothing it lists reasons or it isn't connected). The pick is kept in magpie, settings' agentEfforts by agent (provider.AgentEffort / SetAgentEffort, a level of MemberEfforts or "" for none), and the gateway's candidate loop asks a cursor-local request for it with withFixedEffort, fitted to the model's levels and bounded by a group's, on a model that reasons (the new Provider.Thinks: levels, its list's Reasoning, or models.dev's). Precedence: a group member's fixed effort, then a :effort suffix, then a routing rule's turn pick, then the agent's pick, then the request's own; the pick wins over a level Cursor sent, as Cursor sends its own default as often as a choice, and Default hands the choice back to Cursor. A model that doesn't reason and every other agent's requests go as they came. The Settings page's save carries agentEfforts over as it does fastPicks (TestSettingsSaveKeepsWhatItDoesNotSend's fixture names it). In the window the field sits under "Settings" rather than "New sessions" for this agent alone, as it applies to every request from then on, not to what a session starts on; no new t() strings (Settings, effort and default are translated in zh, ja and de already). TestAgentEffortOnCursorLocal (Chat and Responses with and without a level of their own, Claude on Messages made to think, OpenCode's request untouched, a non-reasoning model untouched, a member fixed at low kept, the pick taken off) fails without the gateway change and passes; TestCursorLocalEffort covers the options (none with no reasoning model, the union of levels, the low/medium/high fallback, none while disconnected), Apply and a bad level refused; both pass -race (-count=20 gateway, -count=10 agent). cursor-local-effort.test.cjs (the window at 560px and the tray panel at 440px: the field under Settings, the slider's five stops with Default first, a pick posting the field, no sideways scroll) passes on Chromium and WebKit in en, zh, ja and de; claude-effort, subagent-effort, agent-field-names, agent-connect, agent-layout, agent-tweak-fold, agent-models, cursor-local-launch and i18n pass on both. go test -tags nogui ./internal/..., go vet, gofmt -l, linux (nogui) and windows builds pass. Not tried with the real Cursor Private Inference: whether it sends a reasoning level of its own on models it shows a Reasoning control for is unverified, which the precedence makes moot. docs/subsystems/gateway-routing.md and agent-wiring.md say it. | ||
|
yetone
|
ec6df1de57 | gateway: a request offering web search is translated on the client's own API where the provider serves it, not on Chat (#997, wlj521: Codex on Xiaomi MiMo's pay as you go showed "Responses → Chat" on v0.1.1082 with all three URLs filled) — Codex offers its web_search tool on every turn, and a provider that doesn't search by itself can't be relayed it: magpie searches for it, which takes a translated request. That translation went to usable's first API, Chat for every model but OpenAI's and Claude's, so on any provider serving Responses (MiMo, whose api.xiaomimimo.com/v1/responses answers 401 to a made-up key, a wrong path 404) each Codex turn went out as Chat, and Claude Code's WebSearch on a provider with an Anthropic URL the same. The translation now stays on the client's API when the provider serves it there and neither ResponsesFirst nor MessagesFirst prefers another (firstElsewhere); the OnMessages check moved before the search check so a Claude model still goes to Messages. The search tool itself isn't sent to the provider (forwardTranslated drops it where the provider doesn't search), and magpie's own web_search function is given on Responses as it was on Chat. TestSearchOfferedStaysOnTheClientsAPI (the preset's three URLs; Codex's Responses with a function and web_search, Claude Code's Messages with web_search_20250305, Chat's web_search_options) and TestCodexSearchAnsweredOnResponses (a searcher configured: the model is asked on /v1/responses twice, the search runs once, Codex gets the answer) fail without the change (/v1/chat/completions) and pass; -race -count=5 on them and TestWebSearch*, TestClaudeFromChat*, TestAutoRelays*. go test ./internal/gateway ./internal/provider, go vet, gofmt -l, linux/windows (nogui) builds pass. Not tried with a real MiMo key (none on this machine) or a real Codex. docs/subsystems/gateway-routing.md says it. | ||
|
zzzpyyy
|
28c58adcb3 | feat(gui): discover local provider configurations with persistent dismissal (#879) | ||
|
yetone
|
e6b0827179 |
gateway, provider: a Claude model is asked on Messages from Chat and Responses too, where its provider has an Anthropic URL (ReturnTrue on Discord, after #997/050e629b: OpenCode on supergpt@claude-opus-5-5 had no cache with Chat, Responses and Anthropic URLs filled; Chat → Anthropic with Anthropic alone wrote 16,318 to the cache) — OpenCode speaks Chat to magpie for every model, Claude's too, and a request on an API the provider serves was relayed as it is, so with a Chat URL beside the Anthropic one OpenCode's Chat went on as Chat and the cache breakpoints the translation to Messages adds never reached the relay; Codex's Responses at a relay with a Responses URL the same. MessagesFirst only ordered the APIs a request is translated to. Provider.OnMessages (MessagesFirst, no "Asked on" set for the model, and no vendor list naming its APIs) now stops the pass-through for Chat and Responses when Messages is usable, and the request is translated there. A model the user pinned to Chat stays on Chat; Copilot's Claude, whose list names Chat and Messages, and every non-Claude model are relayed as before; Messages is relayed as it is. The reporter's second setup (Responses and Anthropic URLs, Chat → Responses in the screenshot) already went to Messages on v0.1.1081 — Chat isn't served there and 050e629b put Messages first — so that screenshot was from before it. TestClaudeFromChatIsAskedOnMessages (the reporter's three setups plus Chat+Anthropic, OpenCode's streamed Chat with a system prompt and a tool and Codex's Responses, each asserting /v1/messages upstream with cache_control in the body) fails without the change on the Chat+Responses+Anthropic and Chat+Anthropic setups and passes; TestClaudePinnedToChatStaysOnChat guards the pin; TestClaudeGoesOnMessagesWhereTheRelayHasThem and TestAutoRelaysOnTheClientsOwnAPI now expect Messages for Claude (GLM and GPT unchanged). -race -count=5 on them and the Copilot tests. go test ./internal/gateway ./internal/provider, go vet (darwin, windows), gofmt -l, darwin, linux (nogui) and windows builds pass. Not tried with the real SuperGPT relay or a real OpenCode. OpenCode's config still names @ai-sdk/openai-compatible for every model; a per-model Anthropic SDK was not added, as it isn't tried with the real OpenCode and the gateway now does the same. docs/subsystems/gateway-routing.md says it.
|
||
|
july_lu
|
51bec20c09 | gui: a gateway key's menu puts its accounts beside their provider's models, not one block at the end (a follow-up to #932, July, LCorleone) — the menu the key's badge opens listed every provider's models and then all the accounts and keys together after them, so "which models" and "which plan" of one provider sat in two far-apart places, hard to give someone one vendor's plan alone. Each provider's accounts and keys now follow its own models, inside its block — the order the /api/caller-keys/models comment already described — an account by who is signed in with the plan in its note, a key by its fingerprint; a provider with accounts and no model in the list (one kept unlisted, or serving none now) keeps its accounts after the models; what the CLI kept that no provider has now stays behind every live entry, a model gone before an account signed out. Nothing of the picking changes: the same proto menu, the same opts and literalName, the same accountsSet that splits what comes back into "models-key" and "accounts-key", and no new strings to translate. gateway-key-accounts reads the order off the real menu now — relay's two accounts between its models and OpenAI's, the key behind GPT-5 — and pins the dead tail on a key held to a gone model and a signed-out account; its last badge read waits for the row to be drawn with the answers (the wait gateway-key-models already makes): without it a slow engine read the hold one action behind, a flake this sandbox shows on main's own test 5/6 runs on WebKit. gateway-key-accounts passes Chromium and WebKit, en and zh; gateway-key-models, gateway-key-groups, gateway-caller-keys, gateway-connect-keys, gateway-key-limit, i18n-keys and usage-keys-fold pass on Chromium — gateway-key-models' scroll assertion doesn't survive this machine's frozen WebKit build on main either. No Go change (the assets are embedded; no Go test reads their content). docs/reference.md's sentence on the menu follows the new order. (#988) | ||
|
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). |