yetone 6294dd0ac5 provider: WorkBuddy usage shows up — send a WorkBuddy User-Agent and read string capacities (workbuddy 订阅的usage能显示出来吗) ...

copilot.tencent.com's gateway answers 10085 '请求不合法' to a request whose
User-Agent it doesn't know, so the resource-summary meter came back rejected
and the credits window stayed empty; every call to it — chat sign included,
not only billing — now goes out as WorkBuddy/<version>. And the meter sends
its capacities as JSON strings ('3300', '438.88000002'), which wouldn't
unmarshal into float64, so a wbNum type parses either a string or a number.
Verified against the live API (GET /console/accounts + POST
/billing/meter/get-user-resource-summary both 200 with the account's real
credits) from app.asar 5.5.6.

2026-09-28 17:40:12 +08:00

..

account_test.go

providers: a removed account's Add it back line can be dismissed for good — Don't remind me beside it hides the line across restarts, and the Add sheet offers the account back under Removed from magpie, one click, for when it's wanted again; removing it again brings the line back (#116)

2026-09-27 22:16:15 +08:00

account.go

provider: WorkBuddy is a subscription — Tencent's CodeBuddy plan, signed in as WorkBuddy does, its own account read too

2026-09-28 16:31:11 +08:00

backup.go

sync: magpie's setup kept the same on every computer through WebDAV (坚果云, Nextcloud, a NAS…) — Settings has Sync and backup: the providers with their keys, groups and icons, the settings, the profiles and each agent's models go to the server as one file sealed with a passphrase, so the server never sees them; the magpie serving the gateway looks every three minutes, sends what changed here and brings in what changed elsewhere, a removal too; a part changed on both sides goes to the newer one, and the copy it replaced is kept in the sync folder with a note saying what was replaced; the proxy and the window size stay each computer's own, and a computer set not to send keys never strips them from the server; Export and Import carry the same file by hand (#28)

2026-09-25 19:52:37 +08:00

balance_test.go

quota: a relay's balance can be told by a sub2api panel, and one that tells none says so — a balance token that is a JWT (a sub2api panel's login token, for GET /api/v1/user/profile) is sent as a Bearer, a new-api access token still as it is, and the editor says which goes there; magpie quota <provider> on one with no balance endpoint gives a line saying it isn't configured and how, --json included, rather than an empty list, and an unknown name is an error

2026-09-28 03:28:17 +08:00

balance.go

quota: a relay's balance can be told by a sub2api panel, and one that tells none says so — a balance token that is a JWT (a sub2api panel's login token, for GET /api/v1/user/profile) is sent as a Bearer, a new-api access token still as it is, and the editor says which goes there; magpie quota <provider> on one with no balance endpoint gives a line saying it isn't configured and how, --json included, rather than an empty list, and an unknown name is an error

2026-09-28 03:28:17 +08:00

catalogs_test.go

providers: an OpenCode model is sent on the API models.dev says it's served on — Grok and GPT on /responses, Claude and MiniMax on /messages — so Claude Code asking OpenCode Go for Grok goes straight to /responses; OpenCode's "Model does not support this protocol" is also taken as the model being served elsewhere

2026-09-27 12:51:43 +08:00

claude_cloak.go

windows: the desktop app no longer opens a console window for every command it runs (#54) — it is linked as a GUI program and has no console, so each console CLI it started (devin auth status and models list, devin acp for every Devin turn, claude, codex, cursor-agent and grok probes and runs, grok login) was given a new console by Windows, and a Windows Terminal window with it, some every few seconds while the app sat idle. Every command magpie runs is now made through internal/proc, which starts it with CREATE_NO_WINDOW when magpie has no console of its own: the child gets a console without a window, and its output, which magpie always pipes back, arrives as before. A magpie run in a terminal (magpie serve, the TUI, the desktop app started from one with a command) has one, and its children share it as they did, so Ctrl+C there still reaches them. The relaunch after an update keeps its DETACHED_PROCESS, added to rather than replacing the flags it was made with, and a test fails on any command made with os/exec directly, so a new one can't bring the windows back

2026-09-25 14:04:44 +08:00

claude_limits_test.go

routing: a Claude account is known once it answers — Claude Code's rate_limit_event (Anthropic's anthropic-ratelimit-unified-* headers: the five hours and the week, used and when they renew) is kept as the account's allowance, standing an hour for a usage endpoint that turns magpie away; and one not known yet goes before those known in smart routing, not after them, where it never answered and so was never known

2026-09-27 20:46:39 +08:00

claude_limits.go

provider: a Claude account's Fable week is read and routed on (#139) — /api/oauth/usage gives a week's allowance per model only in its limits[] array, which readClaudeWindows didn't parse, so magpie accounts, magpie quota and the app never showed Fable's, often the first to run out on Max, and routing went on sending Fable requests to an account whose Fable week was used up. Each weekly_scoped item with a scope.model.display_name is now a window "7 days · <name>", counted in percent, renewing at resets_at, a week long and counting only its model (the name lowercased, spaces and dots as dashes, so "Fable" counts every claude-fable-*), which Allowance.For and Full already weigh against that model alone, as they do the Opus and Sonnet weeks; one without a scope (seven_day again) or one for a model seven_day_opus/seven_day_sonnet already told is left out. Claude Code's rate_limit_event names the same window seven_day_overage_included, its "Fable limit" (in 2.1.283's bundle, for its allowlist Fable, Fable 5, Fable 5.1); claudeKinds takes it too, so the Fable week stays known while the usage endpoint turns magpie away. Reported by Cyb3rN8

2026-09-28 17:12:12 +08:00

claude_scoped_test.go

provider: a Claude account's Fable week is read and routed on (#139) — /api/oauth/usage gives a week's allowance per model only in its limits[] array, which readClaudeWindows didn't parse, so magpie accounts, magpie quota and the app never showed Fable's, often the first to run out on Max, and routing went on sending Fable requests to an account whose Fable week was used up. Each weekly_scoped item with a scope.model.display_name is now a window "7 days · <name>", counted in percent, renewing at resets_at, a week long and counting only its model (the name lowercased, spaces and dots as dashes, so "Fable" counts every claude-fable-*), which Allowance.For and Full already weigh against that model alone, as they do the Opus and Sonnet weeks; one without a scope (seven_day again) or one for a model seven_day_opus/seven_day_sonnet already told is left out. Claude Code's rate_limit_event names the same window seven_day_overage_included, its "Fable limit" (in 2.1.283's bundle, for its allowlist Fable, Fable 5, Fable 5.1); claudeKinds takes it too, so the Fable week stays known while the usage endpoint turns magpie away. Reported by Cyb3rN8

2026-09-28 17:12:12 +08:00

claude_status_test.go

gateway page: opened from a page that already had the providers, it is drawn from them at once rather than left as empty cards until the new list is in (#123) — the skeletons were only for a first load, so coming from Providers showed blank cards for as long as /api/providers took. And Claude Code's sign-in, asked of claude auth status (up to 5s) every 30s under a lock on that path, is served from the last answer while it is asked again behind it

2026-09-28 10:47:42 +08:00

claude_usage_test.go

usage: Claude's allowance is read at most every three minutes per account, and a 429 from Anthropic's usage endpoint keeps what was known — the Usage page, the switch list and routing each asked it every minute for every account, and Anthropic turns an account asked that often away, which left Claude's usage blank or erroring. A turned-away account waits as long as Retry-After says (five minutes when it doesn't), a window that has reset since it was read shows as fresh, and one never read says it is rate limited and when magpie asks again

2026-09-27 09:50:54 +08:00

claude_warmup_test.go

warm-up: Claude accounts too — a Claude window, the 5-hour one and the weekly one, starts at the account's first request after it resets, so with Claude Code warm-up on (Settings: off, weekly, or weekly and 5-hour) the magpie serving the gateway sends each account one "hi" as its window starts over, through Claude Code itself (Haiku, none of its tools, settings or MCP servers, nothing kept on disk), a saved account with its own sign-in; once per reset, kept in claude-warmup.json, as Codex's is

2026-09-28 06:31:40 +08:00

claude_warmup.go

warm-up: Claude accounts too — a Claude window, the 5-hour one and the weekly one, starts at the account's first request after it resets, so with Claude Code warm-up on (Settings: off, weekly, or weekly and 5-hour) the magpie serving the gateway sends each account one "hi" as its window starts over, through Claude Code itself (Haiku, none of its tools, settings or MCP servers, nothing kept on disk), a saved account with its own sign-in; once per reset, kept in claude-warmup.json, as Codex's is

2026-09-28 06:31:40 +08:00

cli_identity_test.go

accounts: a slow or hanging agent CLI no longer holds the providers page (#123) — its timeout now ends the call (a CLI that is a script running node left node holding the output, and the call waited for it however long, the 10s timeouts notwithstanding: a CLI's pipes are closed 2s after); a CLI never answered before is waited for 3s, once, then served as nobody signed in until its answer comes behind; and a CLI saying nobody is signed in is kept like any answer, where before it wasn't and every start waited for it again. Tried with cursor-agent and devin hanging 20s and the network black-holed: the first providers call went from 40.6s to 6s on a first start, and to 13ms on the next

2026-09-28 11:20:14 +08:00

cli_identity.go

accounts: a slow or hanging agent CLI no longer holds the providers page (#123) — its timeout now ends the call (a CLI that is a script running node left node holding the output, and the call waited for it however long, the 10s timeouts notwithstanding: a CLI's pipes are closed 2s after); a CLI never answered before is waited for 3s, once, then served as nobody signed in until its answer comes behind; and a CLI saying nobody is signed in is kept like any answer, where before it wasn't and every start waited for it again. Tried with cursor-agent and devin hanging 20s and the network black-holed: the first providers call went from 40.6s to 6s on a first start, and to 13ms on the next

2026-09-28 11:20:14 +08:00

clinepass_test.go

providers: ClinePass is a preset — Cline's $9.99 plan for open coding models (GLM, Kimi, DeepSeek, MiMo, MiniMax, Qwen), served at the Cline API with a Cline key; the API lists its pay-as-you-go models and not the plan's, so a preset can say what its plan's ids start with (only those of the list are kept) and which they are (given when the list has none)

2026-09-28 10:28:20 +08:00

codex_models_test.go

providers: the context window field offers its usual sizes under it, one click each — 128K, 200K, 256K, 1M — and, where models take more than they are said to, each one's own most: Codex's GPT-6 and GPT-5.6 are said to hold 272K and take 872K when asked, a size nobody remembers, so one chip sets it for every such model (#120). The most is read from max_context_window in the list ChatGPT gives and in Codex CLI's cache

2026-09-28 01:53:08 +08:00

codex_models.go

providers: the context window field offers its usual sizes under it, one click each — 128K, 200K, 256K, 1M — and, where models take more than they are said to, each one's own most: Codex's GPT-6 and GPT-5.6 are said to hold 272K and take 872K when asked, a size nobody remembers, so one chip sets it for every such model (#120). The most is read from max_context_window in the list ChatGPT gives and in Codex CLI's cache

2026-09-28 01:53:08 +08:00

codex_request_test.go

codex: Fast mode through a ChatGPT account — a GPT model Codex's own catalog doesn't list carries the Fast tier Codex gives its GPT models, and the priority service_tier Codex sends for /fast reaches the backend instead of being dropped; other providers' models don't offer it, and other tiers are still left out

2026-09-27 17:42:43 +08:00

codex_request.go

codex: Fast mode through a ChatGPT account — a GPT model Codex's own catalog doesn't list carries the Fast tier Codex gives its GPT models, and the priority service_tier Codex sends for /fast reaches the backend instead of being dropped; other providers' models don't offer it, and other tiers are still left out

2026-09-27 17:42:43 +08:00

codex_switch_test.go

accounts: Codex is signed in to its next ChatGPT account when the one it is on has used its allowance up — the Codex app, knowing its account is out, may not send at all, so magpie's failover never saw the turn: now the magpie serving the gateway looks every five minutes and, with another of Codex's accounts on in magpie that has room, switches Codex to the first of those as the Accounts page would (the one out stays on, next in line); a Codex started after that is on it. An account rests by its user, so the one Codex is switched to doesn't take over the rest of the one it left. Asked on Discord

2026-09-26 21:32:42 +08:00

codex_switch.go

accounts: Codex is signed in to its next ChatGPT account when the one it is on has used its allowance up — the Codex app, knowing its account is out, may not send at all, so magpie's failover never saw the turn: now the magpie serving the gateway looks every five minutes and, with another of Codex's accounts on in magpie that has room, switches Codex to the first of those as the Accounts page would (the one out stays on, next in line); a Codex started after that is on it. An account rests by its user, so the one Codex is switched to doesn't take over the rest of the one it left. Asked on Discord

2026-09-26 21:32:42 +08:00

codex_warmup_test.go

codex: warm-up — a ChatGPT account's next window can be started as soon as the last one resets, by a one-word request to the mini model at low effort, so the 5-hour (or weekly) clock is already running when work begins; Settings → Codex 预热: off, weekly, or weekly and 5-hour. Checked every 5 minutes, only a window seen idle (nothing used, its reset a full span away) is warmed, three tries per reset

2026-09-27 17:36:20 +08:00

codex_warmup.go

warm-up: Claude accounts too — a Claude window, the 5-hour one and the weekly one, starts at the account's first request after it resets, so with Claude Code warm-up on (Settings: off, weekly, or weekly and 5-hour) the magpie serving the gateway sends each account one "hi" as its window starts over, through Claude Code itself (Haiku, none of its tools, settings or MCP servers, nothing kept on disk), a saved account with its own sign-in; once per reset, kept in claude-warmup.json, as Codex's is

2026-09-28 06:31:40 +08:00

context_test.go

providers: test that a subscription's context window set in its editor reaches the models agents are told of (#120) — Codex's 272K from the ChatGPT backend gives way to the 872K a user sets on the Codex account, through the account's save

2026-09-28 00:28:53 +08:00

copilot_accounts_test.go

providers: smart routing, a Copilot subscription signed in from magpie, and import by app in tabs — Smart, now the default, keeps the first key or account while it has quota to spare and moves to the one with the most left as it runs low; one out of credit sits out half an hour, one out of quota until it says it resets, one rate limited as long as the vendor asks, and one failing a minute, longer each time; Copilot gets a tile of its own that signs in with GitHub's device code (the code shown in magpie), several accounts beside the editors' own; Import from other apps shows a tab per app it reads, each with how many providers it has to bring over

2026-09-24 19:41:34 +08:00

copilot_accounts.go

providers: smart routing, a Copilot subscription signed in from magpie, and import by app in tabs — Smart, now the default, keeps the first key or account while it has quota to spare and moves to the one with the most left as it runs low; one out of credit sits out half an hour, one out of quota until it says it resets, one rate limited as long as the vendor asks, and one failing a minute, longer each time; Copilot gets a tile of its own that signs in with GitHub's device code (the code shown in magpie), several accounts beside the editors' own; Import from other apps shows a tab per app it reads, each with how many providers it has to bring over

2026-09-24 19:41:34 +08:00

copilot_cli_test.go

provider: a Copilot CLI sign-in is found — who from ~/.copilot/config.json (JSONC, COPILOT_HOME honoured), the token from the keychain's copilot-cli item or the file's plaintext copilotTokens; the CLI's token is not traded for a session token (that answers 403) but sent as is under the CLI's own integration, at the API its account is served from

2026-09-24 18:24:03 +08:00

copilot_cli.go

windows: the desktop app no longer opens a console window for every command it runs (#54) — it is linked as a GUI program and has no console, so each console CLI it started (devin auth status and models list, devin acp for every Devin turn, claude, codex, cursor-agent and grok probes and runs, grok login) was given a new console by Windows, and a Windows Terminal window with it, some every few seconds while the app sat idle. Every command magpie runs is now made through internal/proc, which starts it with CREATE_NO_WINDOW when magpie has no console of its own: the child gets a console without a window, and its output, which magpie always pipes back, arrives as before. A magpie run in a terminal (magpie serve, the TUI, the desktop app started from one with a command) has one, and its children share it as they did, so Ctrl+C there still reaches them. The relaunch after an update keeps its DETACHED_PROCESS, added to rather than replacing the flags it was made with, and a test fails on any command made with os/exec directly, so a new one can't bring the windows back

2026-09-25 14:04:44 +08:00

copilot_signin.go

providers: smart routing, a Copilot subscription signed in from magpie, and import by app in tabs — Smart, now the default, keeps the first key or account while it has quota to spare and moves to the one with the most left as it runs low; one out of credit sits out half an hour, one out of quota until it says it resets, one rate limited as long as the vendor asks, and one failing a minute, longer each time; Copilot gets a tile of its own that signs in with GitHub's device code (the code shown in magpie), several accounts beside the editors' own; Import from other apps shows a tab per app it reads, each with how many providers it has to bring over

2026-09-24 19:41:34 +08:00

cursor_models.go

cursor: the Run goes to the agent API Cursor's server config names for the account — ServerConfigService/GetServerConfig on api2.cursor.sh, whose agentUrlConfig cursor-agent reads to pick agentUrl in privacy mode (which the Run always asks for) and agentnUrl otherwise — asked once a token, kept by the token's hash so another account asks again, asked afresh and the Run tried once more after a region error, and the global agentn.global.api5.cursor.sh while the config can't be had (retried after a minute), as a team served in one region only was turned away by the global API with 'This region is not yet available for your team'; Cursor's errors have words of their own, no longer Devin's: an unauthenticated or expired sign-in says to sign in to Cursor again in magpie, a region or team restriction says so plainly with a 403 and doesn't ask for a sign-in; and Cursor's expanded ids (grok-4.7-low … grok-4.7-xhigh-fast, Claude with and without thinking, gpt-5.5-extra-high) are offered as one model a family, with the efforts it really has, named as Cursor names its default without the effort and holding what the least of its variants holds, fast and thinking families of their own (GPT-5.5 is 1M, GPT-5.5 Fast isn't said to be) and a family of one kept as Cursor's id — the list saved stays Cursor's own, and the gateway turns model and effort (and Codex's Fast) back into the variant at that effort, Cursor's default for one between those it has, else the nearest, while any of Cursor's own ids still goes as it is

2026-09-28 17:14:07 +08:00

cursor_test.go

cursor: the Run goes to the agent API Cursor's server config names for the account — ServerConfigService/GetServerConfig on api2.cursor.sh, whose agentUrlConfig cursor-agent reads to pick agentUrl in privacy mode (which the Run always asks for) and agentnUrl otherwise — asked once a token, kept by the token's hash so another account asks again, asked afresh and the Run tried once more after a region error, and the global agentn.global.api5.cursor.sh while the config can't be had (retried after a minute), as a team served in one region only was turned away by the global API with 'This region is not yet available for your team'; Cursor's errors have words of their own, no longer Devin's: an unauthenticated or expired sign-in says to sign in to Cursor again in magpie, a region or team restriction says so plainly with a 403 and doesn't ask for a sign-in; and Cursor's expanded ids (grok-4.7-low … grok-4.7-xhigh-fast, Claude with and without thinking, gpt-5.5-extra-high) are offered as one model a family, with the efforts it really has, named as Cursor names its default without the effort and holding what the least of its variants holds, fast and thinking families of their own (GPT-5.5 is 1M, GPT-5.5 Fast isn't said to be) and a family of one kept as Cursor's id — the list saved stays Cursor's own, and the gateway turns model and effort (and Codex's Fast) back into the variant at that effort, Cursor's default for one between those it has, else the nearest, while any of Cursor's own ids still goes as it is

2026-09-28 17:14:07 +08:00

cursor_usage_test.go

cursor: a model is put in Cursor's pool by its family — the server lists grok-4.8, the CLI asks for grok-4.8-high-fast, and the exact match put that one in Other Models; case and cursor- no longer matter, and a bare composer is Cursor's too. The pools read Cursor 模型 / 其他模型 in Chinese

2026-09-28 12:04:43 +08:00

cursor_usage.go

cursor: a model is put in Cursor's pool by its family — the server lists grok-4.8, the CLI asks for grok-4.8-high-fast, and the exact match put that one in Other Models; case and cursor- no longer matter, and a bare composer is Cursor's too. The pools read Cursor 模型 / 其他模型 in Chinese

2026-09-28 12:04:43 +08:00

cursor.go

cursor: the Run goes to the agent API Cursor's server config names for the account — ServerConfigService/GetServerConfig on api2.cursor.sh, whose agentUrlConfig cursor-agent reads to pick agentUrl in privacy mode (which the Run always asks for) and agentnUrl otherwise — asked once a token, kept by the token's hash so another account asks again, asked afresh and the Run tried once more after a region error, and the global agentn.global.api5.cursor.sh while the config can't be had (retried after a minute), as a team served in one region only was turned away by the global API with 'This region is not yet available for your team'; Cursor's errors have words of their own, no longer Devin's: an unauthenticated or expired sign-in says to sign in to Cursor again in magpie, a region or team restriction says so plainly with a 403 and doesn't ask for a sign-in; and Cursor's expanded ids (grok-4.7-low … grok-4.7-xhigh-fast, Claude with and without thinking, gpt-5.5-extra-high) are offered as one model a family, with the efforts it really has, named as Cursor names its default without the effort and holding what the least of its variants holds, fast and thinking families of their own (GPT-5.5 is 1M, GPT-5.5 Fast isn't said to be) and a family of one kept as Cursor's id — the list saved stays Cursor's own, and the gateway turns model and effort (and Codex's Fast) back into the variant at that effort, Cursor's default for one between those it has, else the nearest, while any of Cursor's own ids still goes as it is

2026-09-28 17:14:07 +08:00

decide_test.go

providers: Jev through Vercel's AI Gateway and Cloudflare's Workers AI — two presets, Jev · Vercel AI Gateway and Jev · Cloudflare Workers AI, route groups and pick their effort as TypeSafe's own does, each asked its own way: Vercel's evaluation-model with the model in a header, a noul asked as a boolean and a confidence taken from the probabilities; Workers AI's run of typesafe/jev at the account its API token works in, found once, out of Cloudflare's envelope. A key is checked by the gateway's free call (Vercel's credits, Cloudflare's accounts)

2026-09-28 01:43:09 +08:00

decide.go

providers: Jev through Vercel's AI Gateway and Cloudflare's Workers AI — two presets, Jev · Vercel AI Gateway and Jev · Cloudflare Workers AI, route groups and pick their effort as TypeSafe's own does, each asked its own way: Vercel's evaluation-model with the model in a header, a noul asked as a boolean and a confidence taken from the probabilities; Workers AI's run of typesafe/jev at the account its API token works in, found once, out of Cloudflare's envelope. A key is checked by the gateway's free call (Vercel's credits, Cloudflare's accounts)

2026-09-28 01:43:09 +08:00

devin_test.go

provider: a Devin subscription's own token limits are what agents are told — devin models list gives each variant max_context_tokens and max_output_tokens, and magpie parsed neither, taking the window and the reply cap from models.dev by bare id instead: swe-2's 262000/128000 were written as nothing at all, glm-5.2 at 1M where Devin gives 200K, gpt-5.4 at 922K where Devin gives 272K, grok-4-7's replies at 500K where Devin gives 100K, and gemini-3-8-flash at 1M/65536 from the one provider spelling it that way where Devin gives 1048576/65535 (215 of the 277 variants magpie serves were wrong). The CLI list's numbers are parsed and used, a family's taken from the variant its id follows, a variant without numbers from its family, and models.dev kept for what Devin's list doesn't name or a variant fetched before it was given its family's; a saved list takes Devin's numbers over what an older magpie wrote. Checked against Devin's own model configs, 277 of 277 variants now carry the subscription's numbers (#133)

2026-09-28 15:15:26 +08:00

devin.go

provider: a Devin subscription's own token limits are what agents are told — devin models list gives each variant max_context_tokens and max_output_tokens, and magpie parsed neither, taking the window and the reply cap from models.dev by bare id instead: swe-2's 262000/128000 were written as nothing at all, glm-5.2 at 1M where Devin gives 200K, gpt-5.4 at 922K where Devin gives 272K, grok-4-7's replies at 500K where Devin gives 100K, and gemini-3-8-flash at 1M/65536 from the one provider spelling it that way where Devin gives 1048576/65535 (215 of the 277 variants magpie serves were wrong). The CLI list's numbers are parsed and used, a family's taken from the variant its id follows, a variant without numbers from its family, and models.dev kept for what Devin's list doesn't name or a variant fetched before it was given its family's; a saved list takes Devin's numbers over what an older magpie wrote. Checked against Devin's own model configs, 277 of 277 variants now carry the subscription's numbers (#133)

2026-09-28 15:15:26 +08:00

fallback_test.go

gateway: fallback — when a provider is out of quota, rate limited or down, a request goes to the next model you listed for it, before any of the reply is sent; set it in the provider editor or with magpie provider fallback

2026-09-24 14:04:42 +08:00

favicon_test.go

providers: a custom provider's icon can come from its website (#12) — From the website, beside Choose a picture, finds the site behind the base URL (its host, then the domains it sits under: api.deepseek.com, then deepseek.com) and keeps the icon its home page names (an SVG first, then the apple-touch-icon, data: URIs too) or its /favicon.ico, like a picture picked by hand; only public https hosts are reached. Icons are fetched as magpie, since deepseek.com turns Go's own User-Agent away

2026-09-27 18:52:49 +08:00

favicon.go

providers: a custom provider's icon can come from its website (#12) — From the website, beside Choose a picture, finds the site behind the base URL (its host, then the domains it sits under: api.deepseek.com, then deepseek.com) and keeps the icon its home page names (an SVG first, then the apple-touch-icon, data: URIs too) or its /favicon.ico, like a picture picked by hand; only public https hosts are reached. Icons are fetched as magpie, since deepseek.com turns Go's own User-Agent away

2026-09-27 18:52:49 +08:00

fixv1_test.go

provider: a relay given without its /v1 — one that lists its models at base/v1/models but not at the base — has /v1 added to its chat and responses bases when its models are fetched, since the gateway sends chat to the base as written and its requests 404'd while its models showed; and an Antigravity account Google gave no project says so plainly (with Google's reason, when it gives one) instead of "Usage unavailable" alone

2026-09-25 16:51:26 +08:00

google_test.go

provider + gateway: Google sign-ins — Gemini CLI's and Antigravity's — are subscriptions of magpie's, so any agent can use their models (#4); Gemini CLI's own login in ~/.gemini is read as it is, or an account is signed in from magpie with Google's OAuth, its token refreshed in memory, and each request goes to Code Assist wrapped as the app wraps it, with the project Code Assist set the account up with; Google now serves Gemini CLI's sign-in only to Code Assist Standard and Enterprise, which need a Cloud project, named with magpie accounts project or GOOGLE_CLOUD_PROJECT in ~/.gemini/.env and said so where the account is shown; Google may suspend an Antigravity account used outside Antigravity, so magpie says that and asks before adding one

2026-09-25 15:53:33 +08:00

google.go

provider: a relay given without its /v1 — one that lists its models at base/v1/models but not at the base — has /v1 added to its chat and responses bases when its models are fetched, since the gateway sends chat to the base as written and its requests 404'd while its models showed; and an Antigravity account Google gave no project says so plainly (with Google's reason, when it gives one) instead of "Usage unavailable" alone

2026-09-25 16:51:26 +08:00

grok_accounts_test.go

providers: account usage no longer writes its map from two goroutines at once — an account fetched less than a minute ago went into the map the other accounts' fetches were still writing to, which Go answers with a fatal concurrent map writes, not a panic anything recovers from; LoginUsage and Grok's copy of it now write that hit under the lock their fetches use (#119)

2026-09-27 23:32:15 +08:00

grok_accounts.go

panel: nothing is shaved at an edge (竟然有裁边 / 上面这个border也被裁掉了) — the model's logo on a row's hover comes in as its column opens from nothing to its own width, so a stack of three is as whole as one, with its clip padded past the discs' rings; and the tab's view, which scrolls and so clips at its own top, has the 2px the card's ring outside its box needs, taken from the gap under the tabs. usage: an account's last allowance read is kept (quotas.json beside magpie's settings) and shown in place of one that can't be read for a reason that says nothing about the account — Anthropic rate limiting its usage endpoint, a 5xx, a timeout — across restarts too, with its windows that have reset since starting again from nothing and a tooltip saying when it was read; a reading that comes back is used at once, and a sign-in gone bad is still said (因为rate limit获取不到用量的情况下，能否先暂时用上一次获取到的用量顶替着)

2026-09-28 17:34:08 +08:00

grok_test.go

grok: Codex works on a Grok subscription — the tools Grok's backend turns a request away for (Codex's custom apply_patch, its namespace of agent tools) are left out, and so are web_search's external_web_access and a null content on reasoning handed back, which the backend couldn't decode the encrypted reasoning beside. Tested live: the Codex CLI through magpie counts a file's lines, writes the number and reads it back over several rounds

2026-09-27 20:10:08 +08:00

grok_usage_test.go

provider: a Grok subscription shows its allowance — the account row and the Usage page read the CLI's own /billing credits: this period's share used (weekly for SuperGrok) with when it resets, and on-demand spending against its cap when there is one

2026-09-24 17:49:11 +08:00

grok_usage.go

provider: the Grok subscription is called Grok (SuperGrok) — the plan xAI sells, so it reads as the account it signs into; Grok Build stays the name of the agent, the grok CLI the subscription runs through

2026-09-25 18:33:21 +08:00

grok.go

grok: Codex works on a Grok subscription — the tools Grok's backend turns a request away for (Codex's custom apply_patch, its namespace of agent tools) are left out, and so are web_search's external_web_access and a null content on reasoning handed back, which the backend couldn't decode the encrypted reasoning beside. Tested live: the Codex CLI through magpie counts a file's lines, writes the number and reads it back over several rounds

2026-09-27 20:10:08 +08:00

group_test.go

codex: /fast works on a routing group too — a group with a ChatGPT account's GPT model in it is listed to Codex with the Fast tier, and the service_tier Codex then sends is kept through the group's routing and passed on to OpenAI's own backends (a ChatGPT account, api.openai.com) only; before, the request was rebuilt without it and Fast did nothing

2026-09-27 17:51:38 +08:00

group.go

routing: a group's effort can be picked per turn by any classifier, not only TypeSafe's Jev — a model that isn't a decision API (Jev Router on OpenRouter, Jev on OpenCode Zen, or any small fast model) is asked in words which of low, medium, high or xhigh the turn needs, in a call of its own beside the intent's, and told what the turn before needed; the routing editor offers every model for it

2026-09-27 16:11:23 +08:00

groupnest_test.go

group: a routing group's models can be another group — group/<id> as a member, routed in its place by its own routing and rules, so Coder can be deepseek-v4-pro then Fast, a Coder rule can send a turn to group/fast and Fast's own rules pick within it; a group can't be in itself directly or through another (refused on save, left out of the picker), groups go at most 8 deep, and one can't be removed while another has it. The Routing tab shows a group in a group as a heading with its models under it, the packet going through it, and the log says what each group's rules and classifier decided

2026-09-26 13:41:17 +08:00

grouprename_test.go

group: a group's id can change — a group magpie found is group/auto-<model>, and agents could only pick it by that; now its id (any group's) is changed in the editor or with magpie group set auto-gpt-6-astra id=gpt-6-astra: the found one stays removed under the old id, the groups that have it in them and their rules follow, and an agent set to the old id is told it needs setting again (#83). magpie groups no longer says a group in a group is not served

2026-09-26 14:14:26 +08:00

grouprule_test.go

routing: a request a group's rule sent to a member that can't take it fails over to the members the rules after it that match too name, in their order, before the group's others (#112) — two rules for images, the first's model out of quota, now go on to the second's vision model rather than the group's text-only first; and while the first's rests, the second's goes first. The trace names who comes next, and says a turn stays with whoever took it, not the model the rule named

2026-09-27 20:28:38 +08:00

grouprule.go

routing: a request a group's rule sent to a member that can't take it fails over to the members the rules after it that match too name, in their order, before the group's others (#112) — two rules for images, the first's model out of quota, now go on to the second's vision model rather than the group's text-only first; and while the first's rests, the second's goes first. The trace names who comes next, and says a turn stays with whoever took it, not the model the rule named

2026-09-27 20:28:38 +08:00

icon_test.go

provider: an import link can name the vendor's own icon

2026-09-24 17:13:03 +08:00

icon.go

providers: a custom provider's icon can come from its website (#12) — From the website, beside Choose a picture, finds the site behind the base URL (its host, then the domains it sits under: api.deepseek.com, then deepseek.com) and keeps the icon its home page names (an SVG first, then the apple-touch-icon, data: URIs too) or its /favicon.ico, like a picture picked by hand; only public https hosts are reached. Icons are fetched as magpie, since deepseek.com turns Go's own User-Agent away

2026-09-27 18:52:49 +08:00

import_codex.go

provider: a preset's provider takes request headers of the user's own, and a preset can be added more than once (#50) — which workspace a key that reaches several is for (anthropic-workspace-id), or who the app is to OpenRouter, could only be said by a custom provider, so it meant giving up the preset's endpoints and catalog; the editor now shows headers for presets as well, offering the ones the vendor documents with their values left to fill in, and "Add another" makes one more provider of a preset under an id of its own (anthropic-2) where adding again replaced the first; the same key, host and headers twice is refused as the one already there, and importers keep a preset's headers and its preset when they split an entry off to a free id

2026-09-25 09:36:42 +08:00

importapps_test.go

provider: importing from CC Switch or Alma works on Windows — the database was opened as file://C:/…, which SQLite reads as a host and fails with "out of memory"; it is opened as file:///C:/… now, and the import tests keep USERPROFILE and APPDATA in their sandbox so they never read the machine's own apps

2026-09-25 20:11:28 +08:00

importapps.go

routing: Jev (TypeSafe's System One) as a group's classifier — asked once as a turn begins which of the rules' intents the message is, with how sure it is, and, for a group with effort auto, how hard the turn is to think about; the turn's requests then ask their model for that reasoning, where the agent asked for any. TypeSafe is a decision provider: it serves no conversation and is no group's member

2026-09-27 01:53:04 +08:00

importclaude_test.go

provider: importing from CC Switch or Alma works on Windows — the database was opened as file://C:/…, which SQLite reads as a host and fails with "out of memory"; it is opened as file:///C:/… now, and the import tests keep USERPROFILE and APPDATA in their sandbox so they never read the machine's own apps

2026-09-25 20:11:28 +08:00

importurl_test.go

provider: an import link can name the vendor's own icon

2026-09-24 17:13:03 +08:00

importurl.go

provider: an import link can name the vendor's own icon

2026-09-24 17:13:03 +08:00

install_other.go

provider: a subscription used through its vendor's CLI — Devin's, Cursor's, Grok's — installs that CLI when its sign-in starts, if this machine lacks it, rather than leaving the sign-in to fail or, as Devin's did, to say "signed in" and show nothing: Devin's sign-in wrote credentials.toml, but magpie sees the account only through devin auth status, so with no devin CLI no provider ever came and nothing said why. The sign-in is now "installing" while the vendor's own installer runs (curl … | bash, or its PowerShell one on Windows, with magpie's proxy), then opens the vendor's page as before; the window says what it is installing and why, can cancel it, and a failed install says the installer's last line and the command to run by hand. What counts is the CLI being there afterwards — Devin's installer ends in devin setup, whose sign-in gives up without a terminal and fails the script after it installed everything — and on Windows the PATH the installer wrote is taken up so the running app finds it. A Devin sign-in the CLI then can't see fails, where it said done with no one; the tests no longer see this machine's own devin

2026-09-25 16:30:00 +08:00

install_test.go

provider: a subscription used through its vendor's CLI — Devin's, Cursor's, Grok's — installs that CLI when its sign-in starts, if this machine lacks it, rather than leaving the sign-in to fail or, as Devin's did, to say "signed in" and show nothing: Devin's sign-in wrote credentials.toml, but magpie sees the account only through devin auth status, so with no devin CLI no provider ever came and nothing said why. The sign-in is now "installing" while the vendor's own installer runs (curl … | bash, or its PowerShell one on Windows, with magpie's proxy), then opens the vendor's page as before; the window says what it is installing and why, can cancel it, and a failed install says the installer's last line and the command to run by hand. What counts is the CLI being there afterwards — Devin's installer ends in devin setup, whose sign-in gives up without a terminal and fails the script after it installed everything — and on Windows the PATH the installer wrote is taken up so the running app finds it. A Devin sign-in the CLI then can't see fails, where it said done with no one; the tests no longer see this machine's own devin

2026-09-25 16:30:00 +08:00

install_windows.go

gui: on Windows, Open folder finds Explorer where Windows keeps it — it was looked for on PATH, and a magpie started without the Windows folder on its PATH said exec: "explorer.exe": executable file not found in %PATH%; now %SystemRoot%\explorer.exe. A PATH taken up from the registry after an install had %SystemRoot%\system32 made C:\Windows$\system32; it is expanded as Windows does

2026-09-26 14:22:47 +08:00

install.go

agents: Grok Build — xAI's grok CLI — is an agent: its model is set in ~/.grok/config.toml ($GROK_HOME), and a model through magpie adds the catalog there as [model."magpie/…"] tables pointed at the gateway with magpie's own key, so a request never carries the user's xAI sign-in and the catalog joins Grok's own models in /model; its effort is [models] default_reasoning_effort, its requests are known by grok-shell; the Grok subscription is called Grok Build too

2026-09-25 18:26:50 +08:00

keepalive_test.go

provider: saved accounts are kept signed in — a Claude or ChatGPT account saved in magpie but not the one the agent is on was refreshed only when used or its usage looked at, and smart routing leaves the ones waiting their turn idle for days; the magpie serving the gateway now renews each such sign-in about once a day (hourly check, so a machine that slept catches up), never the agent's own; a refresh the vendor refuses (400/401) marks the account signed out — the account list says to add it again, magpie accounts too — and one that succeeds clears it; magpie accounts refresh renews them all now, for cron or launchd; a switch waits for a refresh in flight, so the agent is never handed a refresh token being spent (#53)

2026-09-25 19:22:37 +08:00

keepalive.go

accounts: a Claude or Codex account removed from magpie is left alone — its sign-ins are no longer saved from the agent nor kept renewed in the background, until it's brought back; before, removing it only kept it out of the providers while magpie went on copying and refreshing the sign-in (#121)

2026-09-28 02:27:36 +08:00

keys_test.go

provider: a key can be made for one protocol — for relays that hand out one key for Anthropic and another for OpenAI; the gateway uses each key on its own endpoint only and sends Claude models to the Anthropic key, GPT models to the OpenAI one, translating when it must

2026-09-24 14:54:56 +08:00

keys.go

provider: a key can be made for one protocol — for relays that hand out one key for Anthropic and another for OpenAI; the gateway uses each key on its own endpoint only and sends Claude models to the Anthropic key, GPT models to the OpenAI one, translating when it must

2026-09-24 14:54:56 +08:00

kiro_main_test.go

providers: Kiro is served through Kiro's own API, as pi-provider-kiro does, not kiro-cli over ACP — magpie reads the sign-in kiro-cli or the Kiro IDE keeps (Google, GitHub, AWS Builder ID / IAM Identity Center, or an external IdP), or takes a Kiro API key saved on the provider, and calls generateAssistantResponse itself: the caller's system prompt, whole history, tools, tool calls and results and images go to the model as they are, with no agent's own prompt and tools between, and its event stream comes back as text, thinking (asked for with Kiro's thinking mode), tool calls streamed as they are written, and usage. kiro-cli no longer has to be installed. A token near its end is refreshed — by kiro-cli when it is its sign-in, else directly, the new one written back where it came from — and one Kiro turns down is refreshed once and the call tried again. History is made the shape Kiro takes: it opens and ends with the user, every call is answered in the next message (an interrupted one said to be so), orphan results go, tools the conversation used but no longer offers are described, ids Kiro rejects are hashed, only the latest images are sent again. Kiro's usage limit is a 429, a prompt too long the error the rest of magpie takes for it. The models are Kiro's list with their context and image support; the account is its email and plan; the Usage page shows its credits and free trial. Issue #90

2026-09-27 01:25:37 +08:00

kiro_test.go

providers: Kiro is served through Kiro's own API, as pi-provider-kiro does, not kiro-cli over ACP — magpie reads the sign-in kiro-cli or the Kiro IDE keeps (Google, GitHub, AWS Builder ID / IAM Identity Center, or an external IdP), or takes a Kiro API key saved on the provider, and calls generateAssistantResponse itself: the caller's system prompt, whole history, tools, tool calls and results and images go to the model as they are, with no agent's own prompt and tools between, and its event stream comes back as text, thinking (asked for with Kiro's thinking mode), tool calls streamed as they are written, and usage. kiro-cli no longer has to be installed. A token near its end is refreshed — by kiro-cli when it is its sign-in, else directly, the new one written back where it came from — and one Kiro turns down is refreshed once and the call tried again. History is made the shape Kiro takes: it opens and ends with the user, every call is answered in the next message (an interrupted one said to be so), orphan results go, tools the conversation used but no longer offers are described, ids Kiro rejects are hashed, only the latest images are sent again. Kiro's usage limit is a 429, a prompt too long the error the rest of magpie takes for it. The models are Kiro's list with their context and image support; the account is its email and plan; the Usage page shows its credits and free trial. Issue #90

2026-09-27 01:25:37 +08:00

kiro.go

providers: Kiro is served through Kiro's own API, as pi-provider-kiro does, not kiro-cli over ACP — magpie reads the sign-in kiro-cli or the Kiro IDE keeps (Google, GitHub, AWS Builder ID / IAM Identity Center, or an external IdP), or takes a Kiro API key saved on the provider, and calls generateAssistantResponse itself: the caller's system prompt, whole history, tools, tool calls and results and images go to the model as they are, with no agent's own prompt and tools between, and its event stream comes back as text, thinking (asked for with Kiro's thinking mode), tool calls streamed as they are written, and usage. kiro-cli no longer has to be installed. A token near its end is refreshed — by kiro-cli when it is its sign-in, else directly, the new one written back where it came from — and one Kiro turns down is refreshed once and the call tried again. History is made the shape Kiro takes: it opens and ends with the user, every call is answered in the next message (an interrupted one said to be so), orphan results go, tools the conversation used but no longer offers are described, ids Kiro rejects are hashed, only the latest images are sent again. Kiro's usage limit is a 429, a prompt too long the error the rest of magpie takes for it. The models are Kiro's list with their context and image support; the account is its email and plan; the Usage page shows its credits and free trial. Issue #90

2026-09-27 01:25:37 +08:00

login_usage.go

panel: nothing is shaved at an edge (竟然有裁边 / 上面这个border也被裁掉了) — the model's logo on a row's hover comes in as its column opens from nothing to its own width, so a stack of three is as whole as one, with its clip padded past the discs' rings; and the tab's view, which scrolls and so clips at its own top, has the 2px the card's ring outside its box needs, taken from the gap under the tabs. usage: an account's last allowance read is kept (quotas.json beside magpie's settings) and shown in place of one that can't be read for a reason that says nothing about the account — Anthropic rate limiting its usage endpoint, a 5xx, a timeout — across restarts too, with its windows that have reset since starting again from nothing and a tooltip saying when it was read; a reading that comes back is used at once, and a sign-in gone bad is still said (因为rate limit获取不到用量的情况下，能否先暂时用上一次获取到的用量顶替着)

2026-09-28 17:34:08 +08:00

logins_on_test.go

providers: account usage no longer writes its map from two goroutines at once — an account fetched less than a minute ago went into the map the other accounts' fetches were still writing to, which Go answers with a fatal concurrent map writes, not a panic anything recovers from; LoginUsage and Grok's copy of it now write that hit under the lock their fetches use (#119)

2026-09-27 23:32:15 +08:00

logins_on.go

provider: WorkBuddy is a subscription — Tencent's CodeBuddy plan, signed in as WorkBuddy does, its own account read too

2026-09-28 16:31:11 +08:00

logins_test.go

provider: deduplicate saved login reads (#126)

2026-09-28 12:01:17 +08:00

logins.go

provider: WorkBuddy is a subscription — Tencent's CodeBuddy plan, signed in as WorkBuddy does, its own account read too

2026-09-28 16:31:11 +08:00

magpie.svg

provider: the page the browser lands on after a sign-in is signed with magpie's mark — the small magpie from build/icon, drawn in the page's muted colour beside the name at its foot, in light and dark

2026-09-25 18:05:37 +08:00

modelprefs_test.go

effort: Claude Code can start at max — settings.json's effortLevel keeps up to xhigh (/effort max lasts a session), so magpie keeps max as CLAUDE_CODE_EFFORT_LEVEL in its env, which every session asks for (tested: Claude Code then sends output_config.effort max), and another level takes it away. A model whose reasoning levels aren't known (one models.dev doesn't list, a custom provider's) can be given some of none…max on the Providers page or with magpie model efforts, which the lists agents get and the gateway then take it to have: a request's effort is fitted to them, max sent as max

2026-09-27 11:05:47 +08:00

modelprefs.go

effort: Claude Code can start at max — settings.json's effortLevel keeps up to xhigh (/effort max lasts a session), so magpie keeps max as CLAUDE_CODE_EFFORT_LEVEL in its env, which every session asks for (tested: Claude Code then sends output_config.effort max), and another level takes it away. A model whose reasoning levels aren't known (one models.dev doesn't list, a custom provider's) can be given some of none…max on the Providers page or with magpie model efforts, which the lists agents get and the gateway then take it to have: a request's effort is fitted to them, max sent as max

2026-09-27 11:05:47 +08:00

models_test.go

provider: a key that is off is no longer asked for its models - Fetch treated len(allKeys()) > 1 as "ask every saved key", and allKeys() includes the KeyAccount entries marked Off, so a disabled or expired key was called on every refresh and its list merged into the catalog, where a text-only answer could take image input off a model a key that is on serves; the live fetch path now uses KeysOn(), off keys get no requests and add nothing to the catalog, and turning a key back on includes it on the next refresh, covered by TestOffKeyIsNotFetched (#76)

2026-09-26 01:06:36 +08:00

models.go

cursor: the Run goes to the agent API Cursor's server config names for the account — ServerConfigService/GetServerConfig on api2.cursor.sh, whose agentUrlConfig cursor-agent reads to pick agentUrl in privacy mode (which the Run always asks for) and agentnUrl otherwise — asked once a token, kept by the token's hash so another account asks again, asked afresh and the Run tried once more after a region error, and the global agentn.global.api5.cursor.sh while the config can't be had (retried after a minute), as a team served in one region only was turned away by the global API with 'This region is not yet available for your team'; Cursor's errors have words of their own, no longer Devin's: an unauthenticated or expired sign-in says to sign in to Cursor again in magpie, a region or team restriction says so plainly with a 403 and doesn't ask for a sign-in; and Cursor's expanded ids (grok-4.7-low … grok-4.7-xhigh-fast, Claude with and without thinking, gpt-5.5-extra-high) are offered as one model a family, with the efforts it really has, named as Cursor names its default without the effort and holding what the least of its variants holds, fast and thinking families of their own (GPT-5.5 is 1M, GPT-5.5 Fast isn't said to be) and a family of one kept as Cursor's id — the list saved stays Cursor's own, and the gateway turns model and effort (and Codex's Fast) back into the variant at that effort, Cursor's default for one between those it has, else the nearest, while any of Cursor's own ids still goes as it is

2026-09-28 17:14:07 +08:00

modelsurl_test.go

provider: a custom provider can list its models from a URL of its own — Xiaomi MiMo's plans are served at their own hosts while the list is at api.xiaomimimo.com/v1/models, so fetching models from the base URL found nothing; More endpoints has a Models URL (模型列表地址), asked with the key and nowhere else, and magpie provider set <id> models.url=… sets it (#67)

2026-09-25 22:16:11 +08:00

normalize_test.go

providers: an Anthropic base URL given as .../v1 or .../v1/messages, as StepFun's docs show it, is taken as its root — magpie asks the root's /v1/messages, so the version went twice and every message was a 404 with nothing to say why, while the model list, asked at both, still answered; StepFun and StepFun (China) are presets, Step Plan or pay as you go

2026-09-27 08:39:08 +08:00

plan_term_test.go

usage: every window says when it starts again, on the clock — "resets 14:30 · in 3h", "tomorrow 09:00", "Fri 00:06" or "Oct 13 00:06" — under its bar on the Usage page, under its meter in the panel, and in the TUI whatever its use (not only once nearly spent) and magpie quota, rather than only in a tooltip

2026-09-28 00:07:47 +08:00

planquota_test.go

usage: a plan says when its paid time ends — a ChatGPT account the date its sign-in names (only while it is ahead: a token not refreshed since says nothing of now), a GLM Coding plan (ZCode, or a Zhipu or Z.ai key) its renewal or end from the account's subscriptions as ZCode reads them — beside the plan on the Usage page, under the account in the panel, and in the TUI and magpie quota

2026-09-27 23:23:56 +08:00

planquota.go

usage: a plan says when its paid time ends — a ChatGPT account the date its sign-in names (only while it is ahead: a token not refreshed since says nothing of now), a GLM Coding plan (ZCode, or a Zhipu or Z.ai key) its renewal or end from the account's subscriptions as ZCode reads them — beside the plan on the Usage page, under the account in the panel, and in the TUI and magpie quota

2026-09-27 23:23:56 +08:00

presets.go

provider: Tencent Cloud Token Plan is a preset — TokenHub's coding subscription (its general and Hy plans on one sk-tp- key, from console.cloud.tencent.com/tokenhub/tokenplan), served at its own endpoints under api.lkeap.cloud.tencent.com/plan: v3 for chat completions and anthropic for messages, no Responses (its Codex page asks for wire_api chat); models.dev lists only its Hy models, so the preset gives the plan's (tc-code-latest, GLM 5–5.3, Kimi K3 and K2.7 Code, DeepSeek V4, MiniMax M3 and M2.7, hy4-preview, hy3) until the plan's own list is fetched, and an entry imported at those endpoints is the preset

2026-09-28 15:41:57 +08:00

provider_test.go

provider: a preset's provider takes request headers of the user's own, and a preset can be added more than once (#50) — which workspace a key that reaches several is for (anthropic-workspace-id), or who the app is to OpenRouter, could only be said by a custom provider, so it meant giving up the preset's endpoints and catalog; the editor now shows headers for presets as well, offering the ones the vendor documents with their values left to fill in, and "Add another" makes one more provider of a preset under an id of its own (anthropic-2) where adding again replaced the first; the same key, host and headers twice is refused as the one already there, and importers keep a preset's headers and its preset when they split an entry off to a free id

2026-09-25 09:36:42 +08:00

provider.go

provider: WorkBuddy is a subscription — Tencent's CodeBuddy plan, signed in as WorkBuddy does, its own account read too

2026-09-28 16:31:11 +08:00

quota_last_test.go

panel: nothing is shaved at an edge (竟然有裁边 / 上面这个border也被裁掉了) — the model's logo on a row's hover comes in as its column opens from nothing to its own width, so a stack of three is as whole as one, with its clip padded past the discs' rings; and the tab's view, which scrolls and so clips at its own top, has the 2px the card's ring outside its box needs, taken from the gap under the tabs. usage: an account's last allowance read is kept (quotas.json beside magpie's settings) and shown in place of one that can't be read for a reason that says nothing about the account — Anthropic rate limiting its usage endpoint, a 5xx, a timeout — across restarts too, with its windows that have reset since starting again from nothing and a tooltip saying when it was read; a reading that comes back is used at once, and a sign-in gone bad is still said (因为rate limit获取不到用量的情况下，能否先暂时用上一次获取到的用量顶替着)

2026-09-28 17:34:08 +08:00

quota_last.go

panel: nothing is shaved at an edge (竟然有裁边 / 上面这个border也被裁掉了) — the model's logo on a row's hover comes in as its column opens from nothing to its own width, so a stack of three is as whole as one, with its clip padded past the discs' rings; and the tab's view, which scrolls and so clips at its own top, has the 2px the card's ring outside its box needs, taken from the gap under the tabs. usage: an account's last allowance read is kept (quotas.json beside magpie's settings) and shown in place of one that can't be read for a reason that says nothing about the account — Anthropic rate limiting its usage endpoint, a 5xx, a timeout — across restarts too, with its windows that have reset since starting again from nothing and a tooltip saying when it was read; a reading that comes back is used at once, and a sign-in gone bad is still said (因为rate limit获取不到用量的情况下，能否先暂时用上一次获取到的用量顶替着)

2026-09-28 17:34:08 +08:00

quotas_dedupe_test.go

usage: gofmt the #90 test

2026-09-26 22:22:30 +08:00

quotas.go

usage: every window says when it starts again, on the clock — "resets 14:30 · in 3h", "tomorrow 09:00", "Fri 00:06" or "Oct 13 00:06" — under its bar on the Usage page, under its meter in the panel, and in the TUI whatever its use (not only once nearly spent) and magpie quota, rather than only in a tooltip

2026-09-28 00:07:47 +08:00

rename_test.go

providers: a provider's id can change — its editor has an ID field (magpie provider set <id> id=<new> in the CLI), and renaming it moves what named it by the old one: the agents on its models (each spelled its own way, recorded as magpie's), the routing groups' members, rules and classifier, other providers' fallbacks, which agents are shown it, and the vendor's fetched list. The old id stays with it, so an agent still running on the old config reaches it, a profile saved before applies to the new id, and its usage so far is counted under the new one. Asked on Discord

2026-09-26 20:22:30 +08:00

rename.go

models: a provider's model can go by a name of the user's, and offer only some of its reasoning levels — Claude Opus 5.5 · Claude Code can be Opus 5.5, and a model with six levels can offer just low, medium and high. Both are kept in settings.json by provider/model (modelNames, modelEfforts), apart from the vendor's list, so a Refresh, a restart or an upgrade leaves them, and the same model from another provider keeps its own; a provider renamed takes them along. They are applied where the catalog is made, so the gateway's /v1/models, the lists magpie writes into the agents (Codex's model catalog, ZCode, Pi, OpenCode, OMP …) and magpie's own pages all show them, and a change rewrites the agents' lists as any other change of the catalog does. Only what is shown changes: the id, where requests go, and the levels the vendor is asked at stay as they were; a found routing group keeps the model's own name. The provider's editor has Names & levels under its models — a name typed in place, a tick per level, Restore default — and the terminal has magpie model name <provider/model> <name>|--reset and magpie model efforts <provider/model> low,medium,high|--reset. Issue #92

2026-09-26 23:23:45 +08:00

routing_test.go

gateway: routing by reset is thorough — only the windows that count a model do (Opus's own weekly allowance used up leaves the account to Sonnet), the week decides and the five hours in it settle a tie, a window whose reset has passed counts as empty, and Grok's on-demand spending and Copilot's completions don't stop an account; the first requests after magpie starts wait a moment for the allowances rather than going in plain order; Copilot's accounts are each asked for their allowance, which renews on the day GitHub says, and have a Usage card each; a subscription out of its allowance rests until the window it filled renews (or when Claude Code says it resets), and is asked again what it has left; "You've hit your limit · resets …" is known as out of quota

2026-09-25 01:57:27 +08:00

routing.go

fix(gateway): 按模型匹配 Cursor 路由额度 (#125)

2026-09-28 12:03:58 +08:00

ruleparse.go

tui: the routing page (3, was groups) does what the app's Routing view does — an open group lists its rules under its models, one list: n adds a rule typed as magpie group rule add takes it (use=<model> tokens=200k images effort=… agents=… intent="…" classifier=<model> at=<n>), ↵ types one again in place, J/K moves it, d twice removes it; c picks the classifier, s how long a conversation stays, x the context agents are told, R renames the group (the page follows it); a found group that was removed is listed last and u brings it back; smart routing is shown as smart, not in order, and o goes round all four. The library page adds too: a adds an MCP server (a URL, or a command) or skills from a GitHub repository or a folder, e changes a server (its env, headers and agents kept), u fetches a skill from GitHub again, s syncs the library into the agents. The rule parsing moves to provider (ParseRule, RuleWords, Rule.Line) and a typed server to library (ServerOf), for the CLI and the TUI alike. Asked on Discord

2026-09-26 23:08:58 +08:00

side_logins.go

provider: WorkBuddy is a subscription — Tencent's CodeBuddy plan, signed in as WorkBuddy does, its own account read too

2026-09-28 16:31:11 +08:00

signedout_test.go

provider: saved Claude or Codex accounts that are not offered say why — under a HOME where the agent is not signed in (a magpie serve with its own HOME, no ~/.codex/auth.json or ~/.claude/.credentials.json there) they went missing without a word; magpie serve, magpie providers and the Providers view now tell

2026-09-26 14:32:48 +08:00

signin_stale_test.go

subscriptions: signing in to Claude over credentials a logout left behind makes the new account the one Claude Code uses — magpie took the stale keychain item and profile for a live sign-in, so the new account was kept beside it unused while Claude Code said it was signed out, and no Claude provider showed up (#31)

2026-09-24 23:10:02 +08:00

signin_team_test.go

provider: a ChatGPT Team workspace on the email of a personal plan is an account of its own, as a Claude Team seat is — accounts were told apart by email alone, so adding one replaced the other and the two took turns (Team and Plus on one email); an account is now its email within a workspace (chatgpt_account_id), and a workspace's is named with its plan (me@example.com · Team) to switch to and remove; one saved under its bare email before is the same account and takes the new name

2026-09-25 14:00:14 +08:00

signin_test.go

provider: add a Claude or ChatGPT subscription from magpie itself — it opens the vendor's sign-in, takes the account when it comes back and lists it with the others, one click from being in use; magpie accounts add <agent> on the command line (#15)

2026-09-24 14:26:37 +08:00

signin.go

provider: WorkBuddy is a subscription — Tencent's CodeBuddy plan, signed in as WorkBuddy does, its own account read too

2026-09-28 16:31:11 +08:00

subscription_usage_test.go

tray: the menu bar's usage says what the panel does — a subscription's quotas are served stale while they refresh behind, and the menu bar, reading them every few minutes, showed each refresh only a tick later (53% beside a panel's 57%); it reads them again the moment a refresh lands

2026-09-28 14:16:42 +08:00

subscription_usage.go

panel: nothing is shaved at an edge (竟然有裁边 / 上面这个border也被裁掉了) — the model's logo on a row's hover comes in as its column opens from nothing to its own width, so a stack of three is as whole as one, with its clip padded past the discs' rings; and the tab's view, which scrolls and so clips at its own top, has the 2px the card's ring outside its box needs, taken from the gap under the tabs. usage: an account's last allowance read is kept (quotas.json beside magpie's settings) and shown in place of one that can't be read for a reason that says nothing about the account — Anthropic rate limiting its usage endpoint, a 5xx, a timeout — across restarts too, with its windows that have reset since starting again from nothing and a tooltip saying when it was read; a reading that comes back is used at once, and a sign-in gone bad is still said (因为rate limit获取不到用量的情况下，能否先暂时用上一次获取到的用量顶替着)

2026-09-28 17:34:08 +08:00

tencent_test.go

provider: Tencent Cloud Token Plan is a preset — TokenHub's coding subscription (its general and Hy plans on one sk-tp- key, from console.cloud.tencent.com/tokenhub/tokenplan), served at its own endpoints under api.lkeap.cloud.tencent.com/plan: v3 for chat completions and anthropic for messages, no Responses (its Codex page asks for wire_api chat); models.dev lists only its Hy models, so the preset gives the plan's (tc-code-latest, GLM 5–5.3, Kimi K3 and K2.7 Code, DeepSeek V4, MiniMax M3 and M2.7, hy4-preview, hy3) until the plan's own list is fetched, and an entry imported at those endpoints is the preset

2026-09-28 15:41:57 +08:00

test_test.go

providers: Test models sends each model agents see a tiny request of its own, on the endpoint it's served on and with a key that sees it, and marks its chip with a dot — green with how long it took, red with what the vendor said — so a relay whose other models answer can't hide one that doesn't (magpie provider test <id> <model>… does it in the terminal). Usage has Hide emails too, one setting with Routing's, to screenshot the subscription cards

2026-09-27 12:26:00 +08:00

test.go

providers: Jev through Vercel's AI Gateway and Cloudflare's Workers AI — two presets, Jev · Vercel AI Gateway and Jev · Cloudflare Workers AI, route groups and pick their effort as TypeSafe's own does, each asked its own way: Vercel's evaluation-model with the model in a header, a noul asked as a boolean and a confidence taken from the probabilities; Workers AI's run of typesafe/jev at the account its API token works in, found once, out of Cloudflare's envelope. A key is checked by the gateway's free call (Vercel's credits, Cloudflare's accounts)

2026-09-28 01:43:09 +08:00

visible.go

models: each agent can be shown only some of them — a provider or group gets a family (magpie provider set relay-x family=relay), and magpie visible zcode relay shows zcode only that family's models (or named providers and groups): in the files magpie writes for it and in what /v1/models answers it, told apart by its User-Agent; magpie models zcode lists what it is shown and what is kept from it, and magpie visible zcode all shows it everything again. A model kept from an agent is still served when asked for by name. Asked for on Discord

2026-09-26 16:02:29 +08:00

workbuddy_test.go

provider: WorkBuddy usage shows up — send a WorkBuddy User-Agent and read string capacities (workbuddy 订阅的usage能显示出来吗)

2026-09-28 17:40:12 +08:00

workbuddy.go

provider: WorkBuddy usage shows up — send a WorkBuddy User-Agent and read string capacities (workbuddy 订阅的usage能显示出来吗)

2026-09-28 17:40:12 +08:00

zcode_test.go

provider(zcode): a ZCode subscription — Z.ai's GLM Coding Plan, as ZCode uses it: ZCode's own account is read from its credential store (~/.zcode/v2/credentials.json, decrypted as ZCode does, never written), and more are added from magpie with ZCode's own sign-in (zcode.z.ai's polling flow, then the account's zcode-api-key, made if missing), kept in logins.json beside it; requests go to the plan's Anthropic endpoint with the key, the models are ZCode's coding-plan list (GLM-5.3, -Flash, 5.2, 5-Turbo), and usage shows the five-hour and weekly credits. A phone sign-in is named by its number

2026-09-26 01:37:01 +08:00

zcode.go

usage: a plan says when its paid time ends — a ChatGPT account the date its sign-in names (only while it is ahead: a token not refreshed since says nothing of now), a GLM Coding plan (ZCode, or a Zhipu or Z.ai key) its renewal or end from the account's subscriptions as ZCode reads them — beside the plan on the Usage page, under the account in the panel, and in the TUI and magpie quota

2026-09-27 23:23:56 +08:00