df019e18e7947cee1e32dc0eccbc4ff9c97a2004
881
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 yetone
|
df019e18e7 | zcode: an old plan with no monthly cap is no longer taken as used up (#366) — the quota reply's TIME_LIMIT is the month's MCP tool calls, which ZCode only shows and never stops the models on, but magpie read it as the account's monthly allowance, so an old plan reporting it at 100% had its ZCode models skipped with the 5 hours full. It is now shown as MCP · Month and set aside, as a pasted Zhipu key's already was, and a limit whose whole is 0 (no cap) counts as unused. TestZCodeNoMonthlyCap fails without the change. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass (the Claude account tests pass alone). | ||
|
Comic Chang
|
49f40b463f |
Configure per-model context windows and output limits (#279)
A provider that serves a model the catalogue does not list, or lists at the wrong size, has a window and a reply limit magpie cannot know: both fall back to whatever the catalogue says about the model's maker, which for such a provider is nothing at all. magpie model context relay-a/gpt-5.5 262144 magpie model output relay-a/gpt-5.5 131072 magpie model context 'relay-a/*' 200000 magpie model output relay-a/gpt-5.5 --reset Both are looked for in the same order as each other: this model, then `<provider id>/*`, then the provider's own list, then the catalogue. A model's own value wins over its provider's. The reply limit is new; the window is not — `Provider.Contexts` has been there, with a `"*"` of its own, settable through `magpie provider set <id> context.<model>=`, and this reuses it rather than shadowing it. That reuse is the point rather than a detail. A context is a routing input and not only a number agents are shown: at 95% of a held member's window a request moves to a member that takes more, so two sources of truth would mean the gateway routing on one number while agents are told another. `magpie model context` is a second way to set the same field, not a second field. Both reach the agents. Pi keeps a model's window and reply limit in its own models.json, OpenCode keeps its limit, and Crush, Droid, Cline, Qoder and Zcode keep their own; an agent reads those files when it starts, so a limit set here that never reaches them is a limit that does not take effect. `magpie provider set` has always told the agents, and this behaves the same way rather than introducing a second, quieter path. The test asserts each setter reaches them exactly once — the two paths differ (one saves the provider file, the other settings and then says so) and that difference is worth pinning. An end-to-end pass confirms it: with a Pi models.json in place, `magpie model context relay-a/sol 999999` writes `contextWindow: 999999` into `providers.magpie.models`. A `0` is refused rather than read as a reset, naming `--reset`; a mistyped model id is refused the way `magpie model name` refuses the same id; a reset says what is actually in force instead of claiming to be back to the vendor's list while a provider-wide value still applies; and `magpie model context <provider>/*` reports that value rather than saying the provider serves no such model. Validation happens where the entry is written, so one hand-edited bad key cannot stop a theme or a window size from saving, and #288's walk moves these on a provider rename without a line here. |
||
|
yetone
|
94ba560257 | plugins: a move installs the plugin as it now matches its built-in (插件版…保持一模一样) — each mover asks for the version published with the parity fixes (WorkBuddy 0.1.3; Command Code, Cursor, Devin, Factory, Kiro, MiMo, Zed, ZCode 0.1.2), updating an older one first, so a failed sign-in says why, a CLI's own account follows its key, refusals read as the built-in's. ZCode's own sign-in on its session alone (the Start Plan) no longer stops the move: zcode-auth 0.1.2 reads ZCode's credentials anew for each request, the session ZCode renews included, so the account goes marked as ZCode's and with no expiry of its own. TestCursorPluginContext and TestMoveDevin no longer lean on the machine: the first seeds its catalog (it failed wherever models.dev's cache wasn't there), the second waits for the fake CLI however loaded the machine. TestZCodeMover fails without the change. Each package installed from npm in an empty HOME comes at the version asked. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass but for TestUserPath and TestClaudeSignedOut, 5s timeouts under the whole run's load that pass alone. | ||
|
yetone
|
44720c6190 |
gateway: Claude Code's WebSearch keeps its metadata through a relay that serves only Claude Code (#359) — a request carrying web_search_20250305 to an Anthropic endpoint other than api.anthropic.com is built again rather than relayed, and the rebuilt body dropped metadata (user_id); a relay limited to the official Claude Code client turned it away with 403. The client's metadata now goes on as sent when an Anthropic request is built for an Anthropic upstream (Bedrock still gets none, as on the relay path, #176). TestClaudeCodeWebSearchKeepsMetadata fails without the change. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass (Claude account tests and TestMoveDevin pass alone; TestCursorPluginContext fails on main since 1ce05f0).
|
||
|
|
1927f82c01 |
Fix model reasoning-level list jumping to top (#357)
* fix(gui): keep provider model list position after level change * gateway: a Claude Code run whose subagent ended on StructuredOutput is let go, and runs left waiting on tool calls are bounded (#345) — a workflow's subagents end on StructuredOutput, which the client answers itself, so the bridge's claude -p waited 30 minutes for a result that never came, one process per subagent. Such a run now waits 30s (for a schema error the client sends at once) and ends; of other runs waiting 5 minutes or more on their caller's tools, 16 are kept, the longest waiting let go first (one that then gets its results starts anew with the whole conversation). TestClaudeRunEndsAfterStructuredOutput and TestClaudeParkedRunsAreBounded fail without the change. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass. * plugins: a built-in moved onto its plugin looks and works as it did (你确保插件版的订阅 provider 和其对应的内置的…都保持一模一样了吗？) — moved onto its plugin, a built-in lost pieces: its tile's name, icon, plans and risk note went to the plugin's own, "Add account" still opened the built-in's sign-in (in the app, on the server and in `magpie accounts add`), an agent's own sign-in the built-in still found showed a second usage card of the same account, the account's plan badge went, WorkBuddy's daily check-in stopped, the provider's icon and site were the plugin's, WorkBuddy AI's card was named WorkBuddy, and Devin, which had no card of its own, lost the plugin's. Now a moved built-in keeps its tile and risk sheet and signs in through its plugin; its cards take the built-in's place and name, and it has none of its own; the plan the plugin tells stays with the account; WorkBuddy checks in through the plugin, which signs the call; a card is left out only where its built-in's slot showed it. TestMovedBuiltinQuiet, TestWorkBuddyCheckinThroughPlugin, TestMoveToPlugin (Devin-like card) and TestPluginUsage (plan kept) fail without the change. Command Code and Devin moved and back in a sandbox HOME: one card each, plan, name. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass; plugin-move, plugin-signin, commandcode-risk, old-webkit pass; click-scroll's WebKit fails the same on origin/main under this load. * provider: the Providers and Gateway pages no longer wait on `claude --version` (deluxe on Discord: on Omarchy the two pages never loaded) — on Omarchy `claude` is a mise wrapper that installs or updates Claude Code before it answers, which on a slow network takes minutes or never ends; magpie asked it with no limit and with a lock held, so /api/providers (fetching the Claude account's models) and every Claude request waited with it. The CLI is now asked in the background, given a minute, and a caller waits at most 3s before the version it has stands in; a late answer is taken once it comes. Reproduced on an Omarchy VM (/api/providers unanswered after 100s on v0.1.516, 3.7s with the change). TestClaudeVersionDoesNotWaitForAStalledCLI and TestClaudeVersionTakenWhenItComes fail without the change. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass. * plugins: a plugin's account behaves as its built-in's (the user: 插件版的订阅 provider 和内置的…保持一模一样了吗) — a plugin's failed sign-in now says why ("the sign-in failed: the sign-in page expired") instead of a bare failure; a plugin account the provider refuses with 401 is marked lapsed, "<user>'s <provider> sign-in has expired — sign in again", beside the account and on its usage card as a built-in's is, and the mark goes when it answers again or is signed in anew; a Devin or Command Code account taken from the agent's CLI moves to the plugin marked as the CLI's and back as the agent's own, so the one it follows stays the one the CLI is signed in to. TestPluginProvider (lapsed), TestMoveSideState (cli) and TestPluginSignIn (reason) fail without the change. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass. * agents: "Hide all" in an agent's model list keeps its line, and an uninstalled Gemini CLI goes from the Agents page (#356, #230) — the line under an agent ("Showing 0 / N models") came only when a picker still listed one of magpie's models, so hiding them all took away the one way back; it now stays while any is hidden. Gemini CLI was taken as present from what it leaves in ~/.gemini (settings.json, .env, installation_id…), which stays after it is uninstalled, so its row stayed, offering to set up a CLI that can't run; it is now its gemini binary. TestAgentModelLineAllHidden and TestGeminiNotAntigravity fail without the change; agent-models-all-hidden.test.cjs (Chromium, WebKit, en/zh) added. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./internal/agent ./internal/gui ./internal/library ./internal/provider pass; agent-models, click-scroll, old-webkit pass. * gateway: Codex's Responses Lite tools reach SuperGrok and every other backend, and a group moves on when a member can't read a request (#350) — Codex sends a Lite model's tools as an additional_tools input item, its own functions in a "functions" namespace; magpie relayed the item to xAI, which 422s on it (unknown item type), and translated routes (Cursor, Anthropic, Chat…) dropped it, so the model had no tools. Outside OpenAI the item's tools now go in tools, the functions namespace opened into plain tools and earlier calls un-namespaced; OpenAI and the ChatGPT account still get Codex's own form. A 400/422 over the request's shape (failed to deserialize, unknown item type/parameter…) now moves to the group's next member, each asked once, the member not resting; the Routing page says so. TestAdditionalToolsRelayed, TestAdditionalToolsTranslated and TestGroupFailsOverARequestShape fail without the change; routing-shape.test.cjs (Chromium, WebKit, en/zh) added. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass; click-scroll, old-webkit, routing-wb-refused pass. * agents: omp's roles pick their own models (subagents, smol, slow), keep their thinking level, and get back what they had before magpie (#325) * agents: omp's subagents and small role pick their own models, through magpie too * agents: omp keeps a role's thinking level and the model it had before magpie, and offers the slow and designer roles A role set to "anthropic/claude-opus-5:max" and switched to a magpie model lost its ":max", and resetting it deleted the key rather than putting the user's model back. The level now goes with the new model (omp clamps one the model lacks, never fails), the model the role had before magpie is stashed and restored, and the reviewer's @slow and the designer's @designer roles are fields beside subagents and small. * gui: omp's slow and designer roles follow the model, as its subagents do Unset, both roles take the session's model, yet the picker offered them omp's Default and no typed model. They are now squares beside subagents, with Same as model first and a model typed in taken as it is. * agents: omp's thinking level no longer hides a role's model from magpie, and the model alone clears it — magpie omp magpie/x/y:high is taken, a role moved back to omp's own is drift, a list of models comes back on reset, and designer (gone in omp 18.1.5) goes A role on "magpie/deepseek/pro:max" matched the picker only through the option offered for its level beside the model, and only for the value in the file now. So the CLI refused a model typed at a level, a recorded value at a level the current one didn't share wasn't known for magpie's (no "replaced" drift), and a level could never be taken away: a model picked without one took the old one on. An agent may now say what it keeps after the model (Agent.SplitSuffix; omp's is its level). Drift, Reseat, RenameProvider, Spell and the CLI's field-for-value match the model and put the suffix back after the one they move to; agents without it are unchanged. The option at the level stays: it keeps the level. Another model keeps it too; the same model picked alone clears it. A role omp falls back through (a YAML list, or the comma list omp joins it into, settings.ts modelRoleValueFromUnknown) read as nothing, so it wasn't stashed and a reset deleted it. It reads as that comma list now, is stashed and comes back; a list has no level of its own. omp 18.1.5 removed the designer role (CHANGELOG), so its field goes. The smol role, like task and slow, gives its agents the session's model when unset; its field is labelled smol, as omp names it, so the GUI can show it as the others without touching other agents' "small". * gui: omp's smol role follows the model as its subagents and slow role do, and designer goes smol unset gives omp's scout and sonic the session's model, so it is a square after the pickers with "Same as model" first, as subagents and slow are (a feather). Its label is smol, not small: OpenCode's, Crush's and OpenChamber's small model stays a picker. designer, a role omp 18.1.5 removed, leaves FOLLOWS_MODEL, the glyphs and i18n. * agents: the note on omp's fallback chains says their keys are roles, and from omp 18 models too ompRefKeys' comment had retry.fallbackChains keyed by model. omp 16.3.5 takes only a role's name there (session/agent-session.ts: "a mapping of role names to selector arrays"); omp 18.4.4 takes a role's name or a model selector (session/retry-fallback-chains.ts). Walking the keys stays: a role's name is no magpie model and is passed over. Follow-up to the review of #340. * agents: omp reads whether it is on magpie one way, and a role at a level that a fallback chain names too is renamed once in each Rebased on #340, one scan over omp's config (ompRefs) answers both questions: magpie's provider stays in models.yml while anything under ompRefKeys is on magpie, as #340 has it, and Check looks at the wiring while any role under modelRoles is, as this PR had it; a fallback chain or enabledModels alone keeps the provider without being checked. A provider renamed moves a role at a thinking level through SplitSuffix first, then RenameRefs the rest, which finds no old name left in the roles: each place moves once, the level kept. * agents: a fallback chain alone on magpie has omp's wiring checked, and a role set off magpie mends it Check now reads the same keys dropMagpie does (ompRefKeys: every role, retry.fallbackChains, enabledModels, task.agentModelOverrides): whatever keeps magpie's provider in models.yml has its baseUrl checked, so a chain on magpie whose wiring something else moved no longer fails its fallback silently. Applying again sets the model role, which may be omp's own; a role set off magpie while something else still names it now writes magpie's provider afresh instead of leaving it as it is, so that mends the wiring. Review of #325. * agents: an omp role that is a list of models stays the user's own, even starting on one of magpie's, and comes back as it was written A role omp falls back through ([magpie/deepseek/flash, openai/gpt-6], or the same as a comma-separated string) was taken for one of magpie's models because it started with magpie/: magpie taking the role over stashed nothing, and a reset deleted it. Only one model, no comma, is magpie's now: SplitSuffix answers whether a value is one model, and Spell, drift (magpieValue), Reseat, RenameProvider and the CLI's fieldForValue leave a list alone. The stash keeps a YAML list as the YAML it was written in (edit.GetYAMLText), and a reset puts it back so, flow or block; a comma-separated string comes back a string. A provider renamed moves the names inside a list through RenameRefs, once, and in the lists the stash keeps too. Review of #325. * gui: a test holds omp's subagents, smol and slow roles as squares that follow the model, and OpenCode's small model a picker omp-roles.test.cjs, in Chromium and WebKit, English and Chinese, API faked: the three roles are squares after the model's picker, unset named "same as model" (「同主模型」) and set naming their model; smol's picker opens on "Same as model" with the model beside it, and a pick sends it and shows it. OpenCode's small model stays a picker. With smol and slow taken out of FOLLOWS_MODEL it fails at "small is a square". Review of #325. * gateway: a Claude Code run whose subagent ended on StructuredOutput is let go, and runs left waiting on tool calls are bounded (#345) — a workflow's subagents end on StructuredOutput, which the client answers itself, so the bridge's claude -p waited 30 minutes for a result that never came, one process per subagent. Such a run now waits 30s (for a schema error the client sends at once) and ends; of other runs waiting 5 minutes or more on their caller's tools, 16 are kept, the longest waiting let go first (one that then gets its results starts anew with the whole conversation). TestClaudeRunEndsAfterStructuredOutput and TestClaudeParkedRunsAreBounded fail without the change. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass. * plugins: a built-in moved onto its plugin looks and works as it did (你确保插件版的订阅 provider 和其对应的内置的…都保持一模一样了吗？) — moved onto its plugin, a built-in lost pieces: its tile's name, icon, plans and risk note went to the plugin's own, "Add account" still opened the built-in's sign-in (in the app, on the server and in `magpie accounts add`), an agent's own sign-in the built-in still found showed a second usage card of the same account, the account's plan badge went, WorkBuddy's daily check-in stopped, the provider's icon and site were the plugin's, WorkBuddy AI's card was named WorkBuddy, and Devin, which had no card of its own, lost the plugin's. Now a moved built-in keeps its tile and risk sheet and signs in through its plugin; its cards take the built-in's place and name, and it has none of its own; the plan the plugin tells stays with the account; WorkBuddy checks in through the plugin, which signs the call; a card is left out only where its built-in's slot showed it. TestMovedBuiltinQuiet, TestWorkBuddyCheckinThroughPlugin, TestMoveToPlugin (Devin-like card) and TestPluginUsage (plan kept) fail without the change. Command Code and Devin moved and back in a sandbox HOME: one card each, plan, name. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass; plugin-move, plugin-signin, commandcode-risk, old-webkit pass; click-scroll's WebKit fails the same on origin/main under this load. * provider: the Providers and Gateway pages no longer wait on `claude --version` (deluxe on Discord: on Omarchy the two pages never loaded) — on Omarchy `claude` is a mise wrapper that installs or updates Claude Code before it answers, which on a slow network takes minutes or never ends; magpie asked it with no limit and with a lock held, so /api/providers (fetching the Claude account's models) and every Claude request waited with it. The CLI is now asked in the background, given a minute, and a caller waits at most 3s before the version it has stands in; a late answer is taken once it comes. Reproduced on an Omarchy VM (/api/providers unanswered after 100s on v0.1.516, 3.7s with the change). TestClaudeVersionDoesNotWaitForAStalledCLI and TestClaudeVersionTakenWhenItComes fail without the change. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass. * plugins: a plugin's account behaves as its built-in's (the user: 插件版的订阅 provider 和内置的…保持一模一样了吗) — a plugin's failed sign-in now says why ("the sign-in failed: the sign-in page expired") instead of a bare failure; a plugin account the provider refuses with 401 is marked lapsed, "<user>'s <provider> sign-in has expired — sign in again", beside the account and on its usage card as a built-in's is, and the mark goes when it answers again or is signed in anew; a Devin or Command Code account taken from the agent's CLI moves to the plugin marked as the CLI's and back as the agent's own, so the one it follows stays the one the CLI is signed in to. TestPluginProvider (lapsed), TestMoveSideState (cli) and TestPluginSignIn (reason) fail without the change. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass. * agents: "Hide all" in an agent's model list keeps its line, and an uninstalled Gemini CLI goes from the Agents page (#356, #230) — the line under an agent ("Showing 0 / N models") came only when a picker still listed one of magpie's models, so hiding them all took away the one way back; it now stays while any is hidden. Gemini CLI was taken as present from what it leaves in ~/.gemini (settings.json, .env, installation_id…), which stays after it is uninstalled, so its row stayed, offering to set up a CLI that can't run; it is now its gemini binary. TestAgentModelLineAllHidden and TestGeminiNotAntigravity fail without the change; agent-models-all-hidden.test.cjs (Chromium, WebKit, en/zh) added. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./internal/agent ./internal/gui ./internal/library ./internal/provider pass; agent-models, click-scroll, old-webkit pass. * gateway: Codex's Responses Lite tools reach SuperGrok and every other backend, and a group moves on when a member can't read a request (#350) — Codex sends a Lite model's tools as an additional_tools input item, its own functions in a "functions" namespace; magpie relayed the item to xAI, which 422s on it (unknown item type), and translated routes (Cursor, Anthropic, Chat…) dropped it, so the model had no tools. Outside OpenAI the item's tools now go in tools, the functions namespace opened into plain tools and earlier calls un-namespaced; OpenAI and the ChatGPT account still get Codex's own form. A 400/422 over the request's shape (failed to deserialize, unknown item type/parameter…) now moves to the group's next member, each asked once, the member not resting; the Routing page says so. TestAdditionalToolsRelayed, TestAdditionalToolsTranslated and TestGroupFailsOverARequestShape fail without the change; routing-shape.test.cjs (Chromium, WebKit, en/zh) added. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass; click-scroll, old-webkit, routing-wb-refused pass. --------- Co-authored-by: yetone <yetoneful@gmail.com> * plugins: a plugin's models show as the built-in's did (插件版…保持一模一样) — a model a plugin says its plan serves at no cost (WorkBuddy's x0.00 credits) is marked free, as the built-in marked it; Cursor's plugin models not named 1M hold what the catalog knows their base to (GPT-4o 128K, Kimi K2 131K), not Cursor's 200K, as the built-in's list; ZCode's own account moves marked as ZCode's, for the plugin (0.1.2) to read ZCode's own sign-in for each request and follow its switches, and comes back as ZCode's own with nothing saved. TestPluginUsage (free), TestCursorPluginContext and TestZCodeMover fail without the change. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass. * agents: Claude Code's effort reaches Opus 5.5 and Sonnet 5.5, follows each model's levels, and gets an ultracode switch (#351, #352, #353, #354) — Claude Code 2.1.251 on reads Opus 5.5's, Sonnet 5.5's and any newer Claude's effort only from modelSettings.<model>.effortLevel, so the top-level effortLevel magpie wrote left them at medium; it now writes modelSettings for the model (and the top key for the models that still read it), and a reset takes out only its own level. The levels offered follow what Claude Code 2.1.285 sends each model: Opus 4.5 low–high, Opus/Sonnet 4.6 without xhigh, Haiku 4.5, Sonnet 4.5 and older none; a level a model doesn't take is refused. A new ultracode square writes "ultracode": true, on models taking xhigh, and magpie claude ultra no longer writes "ultra" as the model. An open session keeps the effort it started with, so a change says to restart it while Claude Code runs. Checked against real Claude Code 2.1.285 in a sandbox HOME with a fake API recording the effort sent. TestClaudeEffortModelSettings, TestClaudeEffortPerModel, TestClaudeUltracode and TestClaudeEffortNotice fail without the change; claude-effort.test.cjs (Chromium, WebKit, en/zh) added. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass; omp-roles, panel-effort, click-scroll, old-webkit pass. * providers: a Remote magpie provider uses another computer's shared magpie, each request translated at most once (Jorben on Discord: 远程 magpie / magpie 接力) — a custom provider pointed at another magpie has one API per address and couldn't know which API each model's own provider serves, so a request was translated on both computers (Chat → Messages here, then again there). magpie's /v1/models now tells each model's native_endpoints (the APIs its provider serves it on; none for a routing group) and its image input, and reads them, with max_output_tokens and supported_reasoning_levels, from a list; the new remote-magpie preset takes the other magpie's address however typed (host:port, /v1, /v1/messages) for all three APIs and lists all its models, its user's choice already. Add sheet tile with the address field and a hint to Settings → Share on local network; CLI: magpie provider add remote-magpie <key> url=http://<ip>:3425. Checked with two sandbox magpies over the LAN address with the key check on and a Messages-only fake upstream: Chat, Messages (streamed), count_tokens, Responses, a routing group and Gemini all reached it as /v1/messages, translated once. TestRemoteMagpieNativeAPI, TestFetchMagpieFields and TestRemoteMagpie fail without the change; remote-magpie.test.cjs (Chromium, WebKit, en/zh) added. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass but for TestCursorPluginContext, which fails on main ( |
||
|
yetone
|
4f9acf72a4 |
subscriptions: Qoder CN, for accounts on qoder.cn (#349) — Qoder's China site (qoder.cn, Alibaba Cloud or phone sign-in) has its own accounts, sign-in page, account API (openapi.qoder.com.cn) and gateway (gateway.qoder.com.cn), so a qoder.cn account couldn't sign in through magpie's Qoder, which only knows qoder.com. A new Qoder CN subscription signs in there with the client id Qoder CN's own CLI sends, and everything after — polling, job token and refresh, user info, models, usage and chat — follows the site saved with the account; if qoder.cn refuses the job token, the account chats with its device token and renews it, as that CLI does. Qoder's tile is now Qoder (international), each tile saying which accounts it is for. Accounts saved before keep working on qoder.com unchanged. Not tried with a real qoder.cn account. TestSites, TestCNDeviceChatRefresh, TestQoderCNSignIn, TestQoderCNDeviceChat, TestQoderGlobalUnchanged and TestQoderCNGateway fail without the change; qoder-cn-tile.test.cjs (Chromium, WebKit, en/zh) added. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass but for TestCursorPluginContext, which fails on main (1ce05f0) as well; click-scroll, old-webkit pass.
|
||
|
yetone
|
ba3c26dec4 |
providers: a Remote magpie provider uses another computer's shared magpie, each request translated at most once (Jorben on Discord: 远程 magpie / magpie 接力) — a custom provider pointed at another magpie has one API per address and couldn't know which API each model's own provider serves, so a request was translated on both computers (Chat → Messages here, then again there). magpie's /v1/models now tells each model's native_endpoints (the APIs its provider serves it on; none for a routing group) and its image input, and reads them, with max_output_tokens and supported_reasoning_levels, from a list; the new remote-magpie preset takes the other magpie's address however typed (host:port, /v1, /v1/messages) for all three APIs and lists all its models, its user's choice already. Add sheet tile with the address field and a hint to Settings → Share on local network; CLI: magpie provider add remote-magpie <key> url=http://<ip>:3425. Checked with two sandbox magpies over the LAN address with the key check on and a Messages-only fake upstream: Chat, Messages (streamed), count_tokens, Responses, a routing group and Gemini all reached it as /v1/messages, translated once. TestRemoteMagpieNativeAPI, TestFetchMagpieFields and TestRemoteMagpie fail without the change; remote-magpie.test.cjs (Chromium, WebKit, en/zh) added. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass but for TestCursorPluginContext, which fails on main (1ce05f0) as well; click-scroll, old-webkit pass.
|
||
|
yetone
|
f1299714bf | agents: Claude Code's effort reaches Opus 5.5 and Sonnet 5.5, follows each model's levels, and gets an ultracode switch (#351, #352, #353, #354) — Claude Code 2.1.251 on reads Opus 5.5's, Sonnet 5.5's and any newer Claude's effort only from modelSettings.<model>.effortLevel, so the top-level effortLevel magpie wrote left them at medium; it now writes modelSettings for the model (and the top key for the models that still read it), and a reset takes out only its own level. The levels offered follow what Claude Code 2.1.285 sends each model: Opus 4.5 low–high, Opus/Sonnet 4.6 without xhigh, Haiku 4.5, Sonnet 4.5 and older none; a level a model doesn't take is refused. A new ultracode square writes "ultracode": true, on models taking xhigh, and magpie claude ultra no longer writes "ultra" as the model. An open session keeps the effort it started with, so a change says to restart it while Claude Code runs. Checked against real Claude Code 2.1.285 in a sandbox HOME with a fake API recording the effort sent. TestClaudeEffortModelSettings, TestClaudeEffortPerModel, TestClaudeUltracode and TestClaudeEffortNotice fail without the change; claude-effort.test.cjs (Chromium, WebKit, en/zh) added. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass; omp-roles, panel-effort, click-scroll, old-webkit pass. | ||
|
yetone
|
1ce05f0270 | plugins: a plugin's models show as the built-in's did (插件版…保持一模一样) — a model a plugin says its plan serves at no cost (WorkBuddy's x0.00 credits) is marked free, as the built-in marked it; Cursor's plugin models not named 1M hold what the catalog knows their base to (GPT-4o 128K, Kimi K2 131K), not Cursor's 200K, as the built-in's list; ZCode's own account moves marked as ZCode's, for the plugin (0.1.2) to read ZCode's own sign-in for each request and follow its switches, and comes back as ZCode's own with nothing saved. TestPluginUsage (free), TestCursorPluginContext and TestZCodeMover fail without the change. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass. | ||
|
cyxer000andyetone
|
1ec5495b26 |
agents: omp's roles pick their own models (subagents, smol, slow), keep their thinking level, and get back what they had before magpie (#325)
* agents: omp's subagents and small role pick their own models, through magpie too * agents: omp keeps a role's thinking level and the model it had before magpie, and offers the slow and designer roles A role set to "anthropic/claude-opus-5:max" and switched to a magpie model lost its ":max", and resetting it deleted the key rather than putting the user's model back. The level now goes with the new model (omp clamps one the model lacks, never fails), the model the role had before magpie is stashed and restored, and the reviewer's @slow and the designer's @designer roles are fields beside subagents and small. * gui: omp's slow and designer roles follow the model, as its subagents do Unset, both roles take the session's model, yet the picker offered them omp's Default and no typed model. They are now squares beside subagents, with Same as model first and a model typed in taken as it is. * agents: omp's thinking level no longer hides a role's model from magpie, and the model alone clears it — magpie omp magpie/x/y:high is taken, a role moved back to omp's own is drift, a list of models comes back on reset, and designer (gone in omp 18.1.5) goes A role on "magpie/deepseek/pro:max" matched the picker only through the option offered for its level beside the model, and only for the value in the file now. So the CLI refused a model typed at a level, a recorded value at a level the current one didn't share wasn't known for magpie's (no "replaced" drift), and a level could never be taken away: a model picked without one took the old one on. An agent may now say what it keeps after the model (Agent.SplitSuffix; omp's is its level). Drift, Reseat, RenameProvider, Spell and the CLI's field-for-value match the model and put the suffix back after the one they move to; agents without it are unchanged. The option at the level stays: it keeps the level. Another model keeps it too; the same model picked alone clears it. A role omp falls back through (a YAML list, or the comma list omp joins it into, settings.ts modelRoleValueFromUnknown) read as nothing, so it wasn't stashed and a reset deleted it. It reads as that comma list now, is stashed and comes back; a list has no level of its own. omp 18.1.5 removed the designer role (CHANGELOG), so its field goes. The smol role, like task and slow, gives its agents the session's model when unset; its field is labelled smol, as omp names it, so the GUI can show it as the others without touching other agents' "small". * gui: omp's smol role follows the model as its subagents and slow role do, and designer goes smol unset gives omp's scout and sonic the session's model, so it is a square after the pickers with "Same as model" first, as subagents and slow are (a feather). Its label is smol, not small: OpenCode's, Crush's and OpenChamber's small model stays a picker. designer, a role omp 18.1.5 removed, leaves FOLLOWS_MODEL, the glyphs and i18n. * agents: the note on omp's fallback chains says their keys are roles, and from omp 18 models too ompRefKeys' comment had retry.fallbackChains keyed by model. omp 16.3.5 takes only a role's name there (session/agent-session.ts: "a mapping of role names to selector arrays"); omp 18.4.4 takes a role's name or a model selector (session/retry-fallback-chains.ts). Walking the keys stays: a role's name is no magpie model and is passed over. Follow-up to the review of #340. * agents: omp reads whether it is on magpie one way, and a role at a level that a fallback chain names too is renamed once in each Rebased on #340, one scan over omp's config (ompRefs) answers both questions: magpie's provider stays in models.yml while anything under ompRefKeys is on magpie, as #340 has it, and Check looks at the wiring while any role under modelRoles is, as this PR had it; a fallback chain or enabledModels alone keeps the provider without being checked. A provider renamed moves a role at a thinking level through SplitSuffix first, then RenameRefs the rest, which finds no old name left in the roles: each place moves once, the level kept. * agents: a fallback chain alone on magpie has omp's wiring checked, and a role set off magpie mends it Check now reads the same keys dropMagpie does (ompRefKeys: every role, retry.fallbackChains, enabledModels, task.agentModelOverrides): whatever keeps magpie's provider in models.yml has its baseUrl checked, so a chain on magpie whose wiring something else moved no longer fails its fallback silently. Applying again sets the model role, which may be omp's own; a role set off magpie while something else still names it now writes magpie's provider afresh instead of leaving it as it is, so that mends the wiring. Review of #325. * agents: an omp role that is a list of models stays the user's own, even starting on one of magpie's, and comes back as it was written A role omp falls back through ([magpie/deepseek/flash, openai/gpt-6], or the same as a comma-separated string) was taken for one of magpie's models because it started with magpie/: magpie taking the role over stashed nothing, and a reset deleted it. Only one model, no comma, is magpie's now: SplitSuffix answers whether a value is one model, and Spell, drift (magpieValue), Reseat, RenameProvider and the CLI's fieldForValue leave a list alone. The stash keeps a YAML list as the YAML it was written in (edit.GetYAMLText), and a reset puts it back so, flow or block; a comma-separated string comes back a string. A provider renamed moves the names inside a list through RenameRefs, once, and in the lists the stash keeps too. Review of #325. * gui: a test holds omp's subagents, smol and slow roles as squares that follow the model, and OpenCode's small model a picker omp-roles.test.cjs, in Chromium and WebKit, English and Chinese, API faked: the three roles are squares after the model's picker, unset named "same as model" (「同主模型」) and set naming their model; smol's picker opens on "Same as model" with the model beside it, and a pick sends it and shows it. OpenCode's small model stays a picker. With smol and slow taken out of FOLLOWS_MODEL it fails at "small is a square". Review of #325. * gateway: a Claude Code run whose subagent ended on StructuredOutput is let go, and runs left waiting on tool calls are bounded (#345) — a workflow's subagents end on StructuredOutput, which the client answers itself, so the bridge's claude -p waited 30 minutes for a result that never came, one process per subagent. Such a run now waits 30s (for a schema error the client sends at once) and ends; of other runs waiting 5 minutes or more on their caller's tools, 16 are kept, the longest waiting let go first (one that then gets its results starts anew with the whole conversation). TestClaudeRunEndsAfterStructuredOutput and TestClaudeParkedRunsAreBounded fail without the change. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass. * plugins: a built-in moved onto its plugin looks and works as it did (你确保插件版的订阅 provider 和其对应的内置的…都保持一模一样了吗？) — moved onto its plugin, a built-in lost pieces: its tile's name, icon, plans and risk note went to the plugin's own, "Add account" still opened the built-in's sign-in (in the app, on the server and in `magpie accounts add`), an agent's own sign-in the built-in still found showed a second usage card of the same account, the account's plan badge went, WorkBuddy's daily check-in stopped, the provider's icon and site were the plugin's, WorkBuddy AI's card was named WorkBuddy, and Devin, which had no card of its own, lost the plugin's. Now a moved built-in keeps its tile and risk sheet and signs in through its plugin; its cards take the built-in's place and name, and it has none of its own; the plan the plugin tells stays with the account; WorkBuddy checks in through the plugin, which signs the call; a card is left out only where its built-in's slot showed it. TestMovedBuiltinQuiet, TestWorkBuddyCheckinThroughPlugin, TestMoveToPlugin (Devin-like card) and TestPluginUsage (plan kept) fail without the change. Command Code and Devin moved and back in a sandbox HOME: one card each, plan, name. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass; plugin-move, plugin-signin, commandcode-risk, old-webkit pass; click-scroll's WebKit fails the same on origin/main under this load. * provider: the Providers and Gateway pages no longer wait on `claude --version` (deluxe on Discord: on Omarchy the two pages never loaded) — on Omarchy `claude` is a mise wrapper that installs or updates Claude Code before it answers, which on a slow network takes minutes or never ends; magpie asked it with no limit and with a lock held, so /api/providers (fetching the Claude account's models) and every Claude request waited with it. The CLI is now asked in the background, given a minute, and a caller waits at most 3s before the version it has stands in; a late answer is taken once it comes. Reproduced on an Omarchy VM (/api/providers unanswered after 100s on v0.1.516, 3.7s with the change). TestClaudeVersionDoesNotWaitForAStalledCLI and TestClaudeVersionTakenWhenItComes fail without the change. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass. * plugins: a plugin's account behaves as its built-in's (the user: 插件版的订阅 provider 和内置的…保持一模一样了吗) — a plugin's failed sign-in now says why ("the sign-in failed: the sign-in page expired") instead of a bare failure; a plugin account the provider refuses with 401 is marked lapsed, "<user>'s <provider> sign-in has expired — sign in again", beside the account and on its usage card as a built-in's is, and the mark goes when it answers again or is signed in anew; a Devin or Command Code account taken from the agent's CLI moves to the plugin marked as the CLI's and back as the agent's own, so the one it follows stays the one the CLI is signed in to. TestPluginProvider (lapsed), TestMoveSideState (cli) and TestPluginSignIn (reason) fail without the change. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass. * agents: "Hide all" in an agent's model list keeps its line, and an uninstalled Gemini CLI goes from the Agents page (#356, #230) — the line under an agent ("Showing 0 / N models") came only when a picker still listed one of magpie's models, so hiding them all took away the one way back; it now stays while any is hidden. Gemini CLI was taken as present from what it leaves in ~/.gemini (settings.json, .env, installation_id…), which stays after it is uninstalled, so its row stayed, offering to set up a CLI that can't run; it is now its gemini binary. TestAgentModelLineAllHidden and TestGeminiNotAntigravity fail without the change; agent-models-all-hidden.test.cjs (Chromium, WebKit, en/zh) added. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./internal/agent ./internal/gui ./internal/library ./internal/provider pass; agent-models, click-scroll, old-webkit pass. * gateway: Codex's Responses Lite tools reach SuperGrok and every other backend, and a group moves on when a member can't read a request (#350) — Codex sends a Lite model's tools as an additional_tools input item, its own functions in a "functions" namespace; magpie relayed the item to xAI, which 422s on it (unknown item type), and translated routes (Cursor, Anthropic, Chat…) dropped it, so the model had no tools. Outside OpenAI the item's tools now go in tools, the functions namespace opened into plain tools and earlier calls un-namespaced; OpenAI and the ChatGPT account still get Codex's own form. A 400/422 over the request's shape (failed to deserialize, unknown item type/parameter…) now moves to the group's next member, each asked once, the member not resting; the Routing page says so. TestAdditionalToolsRelayed, TestAdditionalToolsTranslated and TestGroupFailsOverARequestShape fail without the change; routing-shape.test.cjs (Chromium, WebKit, en/zh) added. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass; click-scroll, old-webkit, routing-wb-refused pass. --------- Co-authored-by: yetone <yetoneful@gmail.com> |
||
|
yetone
|
4ead7c84a3 | gateway: Codex's Responses Lite tools reach SuperGrok and every other backend, and a group moves on when a member can't read a request (#350) — Codex sends a Lite model's tools as an additional_tools input item, its own functions in a "functions" namespace; magpie relayed the item to xAI, which 422s on it (unknown item type), and translated routes (Cursor, Anthropic, Chat…) dropped it, so the model had no tools. Outside OpenAI the item's tools now go in tools, the functions namespace opened into plain tools and earlier calls un-namespaced; OpenAI and the ChatGPT account still get Codex's own form. A 400/422 over the request's shape (failed to deserialize, unknown item type/parameter…) now moves to the group's next member, each asked once, the member not resting; the Routing page says so. TestAdditionalToolsRelayed, TestAdditionalToolsTranslated and TestGroupFailsOverARequestShape fail without the change; routing-shape.test.cjs (Chromium, WebKit, en/zh) added. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass; click-scroll, old-webkit, routing-wb-refused pass. | ||
|
yetone
|
c47b22ee27 | agents: "Hide all" in an agent's model list keeps its line, and an uninstalled Gemini CLI goes from the Agents page (#356, #230) — the line under an agent ("Showing 0 / N models") came only when a picker still listed one of magpie's models, so hiding them all took away the one way back; it now stays while any is hidden. Gemini CLI was taken as present from what it leaves in ~/.gemini (settings.json, .env, installation_id…), which stays after it is uninstalled, so its row stayed, offering to set up a CLI that can't run; it is now its gemini binary. TestAgentModelLineAllHidden and TestGeminiNotAntigravity fail without the change; agent-models-all-hidden.test.cjs (Chromium, WebKit, en/zh) added. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./internal/agent ./internal/gui ./internal/library ./internal/provider pass; agent-models, click-scroll, old-webkit pass. | ||
|
yetone
|
ee5b1b7d44 | plugins: a plugin's account behaves as its built-in's (the user: 插件版的订阅 provider 和内置的…保持一模一样了吗) — a plugin's failed sign-in now says why ("the sign-in failed: the sign-in page expired") instead of a bare failure; a plugin account the provider refuses with 401 is marked lapsed, "<user>'s <provider> sign-in has expired — sign in again", beside the account and on its usage card as a built-in's is, and the mark goes when it answers again or is signed in anew; a Devin or Command Code account taken from the agent's CLI moves to the plugin marked as the CLI's and back as the agent's own, so the one it follows stays the one the CLI is signed in to. TestPluginProvider (lapsed), TestMoveSideState (cli) and TestPluginSignIn (reason) fail without the change. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass. | ||
|
yetone
|
424ff31a46 |
provider: the Providers and Gateway pages no longer wait on claude --version (deluxe on Discord: on Omarchy the two pages never loaded) — on Omarchy claude is a mise wrapper that installs or updates Claude Code before it answers, which on a slow network takes minutes or never ends; magpie asked it with no limit and with a lock held, so /api/providers (fetching the Claude account's models) and every Claude request waited with it. The CLI is now asked in the background, given a minute, and a caller waits at most 3s before the version it has stands in; a late answer is taken once it comes. Reproduced on an Omarchy VM (/api/providers unanswered after 100s on v0.1.516, 3.7s with the change). TestClaudeVersionDoesNotWaitForAStalledCLI and TestClaudeVersionTakenWhenItComes fail without the change. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass.
|
||
|
yetone
|
4a0fbc332c |
plugins: a built-in moved onto its plugin looks and works as it did (你确保插件版的订阅 provider 和其对应的内置的…都保持一模一样了吗？) — moved onto its plugin, a built-in lost pieces: its tile's name, icon, plans and risk note went to the plugin's own, "Add account" still opened the built-in's sign-in (in the app, on the server and in magpie accounts add), an agent's own sign-in the built-in still found showed a second usage card of the same account, the account's plan badge went, WorkBuddy's daily check-in stopped, the provider's icon and site were the plugin's, WorkBuddy AI's card was named WorkBuddy, and Devin, which had no card of its own, lost the plugin's. Now a moved built-in keeps its tile and risk sheet and signs in through its plugin; its cards take the built-in's place and name, and it has none of its own; the plan the plugin tells stays with the account; WorkBuddy checks in through the plugin, which signs the call; a card is left out only where its built-in's slot showed it. TestMovedBuiltinQuiet, TestWorkBuddyCheckinThroughPlugin, TestMoveToPlugin (Devin-like card) and TestPluginUsage (plan kept) fail without the change. Command Code and Devin moved and back in a sandbox HOME: one card each, plan, name. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass; plugin-move, plugin-signin, commandcode-risk, old-webkit pass; click-scroll's WebKit fails the same on origin/main under this load.
|
||
|
yetone
|
139cc6590a | gateway: a Claude Code run whose subagent ended on StructuredOutput is let go, and runs left waiting on tool calls are bounded (#345) — a workflow's subagents end on StructuredOutput, which the client answers itself, so the bridge's claude -p waited 30 minutes for a result that never came, one process per subagent. Such a run now waits 30s (for a schema error the client sends at once) and ends; of other runs waiting 5 minutes or more on their caller's tools, 16 are kept, the longest waiting let go first (one that then gets its results starts anew with the whole conversation). TestClaudeRunEndsAfterStructuredOutput and TestClaudeParkedRunsAreBounded fail without the change. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass. | ||
|
cyxer000
|
f3b45634a3 | agents: Droid, Qoder, OpenHanako, WorkBuddy, OpenCode and ZCode no longer get an output limit above the model's context window (#347) | ||
|
cyxer000
|
abbffd73a4 |
agents: magpie omp auto sets omp's thinking to auto, and the panel's effort slider shows a level it doesn't list as it is (#339)
* agents: `magpie omp auto` sets omp's thinking to auto, and the panel's effort slider shows a level it doesn't list as it is omp keeps defaultThinkingLevel at minimal … max or auto (omp picks a level each turn), but magpie offered only the six levels. So `magpie omp auto` found no field offering auto and took it for a model: modelRoles.default became the literal "auto". auto is now offered first, as omp's own picker has it, and kept out of ompEfforts, which a model's thinking levels in models.yml are filtered by. The tray panel's effort slider drew a value that isn't one of its options (an agent with no effort set, a level magpie doesn't list) at the first stop, named as the lowest level, and a touch there wrote that level over it. It now gets a stop of its own, as the window's picker gives the current value, so it reads as it is and a touch leaves it. * agents: the note on omp's thinking picker holds for omp 16.3.5 too omp 16.3.5 takes auto for defaultThinkingLevel as 18.4.4 does (config/settings-schema.ts there), as checked on #339. |
||
|
cyxer000
|
49f02c6f03 |
agents: omp's requests through magpie are known for omp's on omp 16 too (#343)
omp 16.3.5 asks a custom provider with Bun's User-Agent (Bun/1.3.14), and only omp 18 with its own (omp/18.4.4), so the gateway counted omp 16's requests as Bun's and passed over omp's rules and stand-ins. magpie's provider in models.yml now carries User-Agent: omp, as it does for Hermes and Cline. Checked with omp 16.3.5 and 18.4.4: both send it and accept the file. TestOmpNamedToTheGateway fails without the change. |
||
|
cyxer000
|
110567472d |
edit: a config that is a hard link stays one when magpie saves or clears it (#328)
* edit: a config that is a hard link stays one when magpie saves or clears it — WriteAtomic renamed a temp file over the path even when the file had other names, so a models.yml that Orca keeps hard-linked into its overlay split in two: omp's name got the new text, the overlay kept the old one, and each later write drifted further; clearing an instructions file unlinked only magpie's name and left the old text under the others. Now a regular file with more than one link (st_nlink on unix, NumberOfLinks from GetFileInformationByHandle on Windows, one elsewhere) is written in place: the new text first goes to a temp file beside it and is synced, then is written over the file, cut to length and synced, and the temp file goes; a crash part way leaves the whole new text beside it, and a failed write keeps it and names it in the error. Mode, owner and every name stay. Remove empties such a file instead of unlinking one name, as it already did for a symlink, and a failed edit rolled back by Atomically goes back in place too. A file with one link is still replaced by rename, atomically, as before. * edit: a read-only hard-linked config is still written, and temp files a crashed write left beside a config go at its next write Review follow-up on #328: - A hard-linked file that can't be opened for writing (0444 on unix, read-only on Windows) fell over with "permission denied" where main's rename replaced it. WriteAtomic now opens it first and, on fs.ErrPermission, falls back to temp file + rename as before, which splits that name from the others as main always did. On Windows main couldn't rename over a read-only file either, so nothing changes there. - writeInPlace says why it writes over and then cuts to length: a reader can briefly see the new text with the old one's tail, but emptying first would show an empty or half file instead, which a tool may load as a config with nothing set; a mangled one fails to parse. - writeInPlace names the trade with hard-link backups (rsnapshot, cp -al, rsync --link-dest): they change with the file, as with vim's backupcopy=auto. - Remove says that emptying every name is meant: with AGENTS.md and CLAUDE.md one file, clearing one empties both, as #323 does for a symlink's target, since deleting one name would leave the text magpie is taking back under the other. - After a write goes through, both paths remove .<name>.<digits>.tmp beside the file older than ten minutes: the file then holds newer text than any of them, a fresh one may be another write's still under way, and the digits keep other files' temps (.models.yml.bak.1.tmp) out. |
||
|
yetone
|
2c432fe3fa | routing, models: a rerouted request's tooltip names who answered it (#337), and model names can go without their provider (#335) — the Routing page's and the tray panel's rows named the member that answered a rerouted request, but their tooltip still said the path first resolved; it now says the provider · account · model that answered, and on a second line what it was rerouted from. A setting, Settings → Preferences "Provider in model names" or magpie model suffix off (on by default, as before), writes the models listed to Codex and the other agents (OpenCode, Pi, omp…) by their name alone, except two in an agent's list that would read the same, which keep theirs. routing-reroute-title.test.cjs and plain-names.test.cjs (Chromium, WebKit, en/zh), TestPlainNames, TestPlainNamesReachAgents and TestModelSuffixCmd fail without the change; click-scroll, old-webkit, currency, text-size, panel-routing, routing-served, routing-steady pass. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass. | ||
|
yetone
|
adde88ef23 | agents: Kimi Code offers a model's thinking levels, and the level picked reaches the model (#333) — the new Kimi Code (2.x) builds its thinking picker from a model's support_efforts and default_effort, which magpie never wrote, so it offered thinking only on or off. magpie now writes the model's levels (none left out: Kimi Code's Off is that) and default_effort high when the model has it, to ~/.kimi-code only; the old kimi-cli's schema has neither. Kimi Code sends the level inside thinking ({"type":"enabled","effort":…}), not as reasoning_effort, so the gateway moves it there on a Chat request that doesn't say reasoning_effort itself, and fits it like any other agent's. Checked with the real kimi CLI (2.1.1) in a sandbox HOME against a fake upstream: kimi doctor passes, /model shows Off Low Medium High Max, a pick reaches upstream as reasoning_effort; unknown values don't make it reject the file. TestKimiEfforts and TestKimiCodeEffortReachesChatVendor fail without the change. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass. | ||
|
yetone
|
f5f10bda4d | plugins: a plugin's accounts show their allowance as the built-ins' do (the user: 所有插件要完整支持显示额度！跟内置一模一样！) — a plugin's auth.usage now tells plan, user, until, renew, balance, resets (count, until, by window, five hours, weekly) and windows (used past 100 when overspent, resets at/in, display, span, the models a window counts or leaves out, aside), and magpie shows them on the usage page, in the menu bar, beside each account and to the gateway, which passes over an account used up for the model asked; a built-in moved onto its plugin keeps its card's name and icon. Also: Command Code's subscription endpoint answering 200 {"success":false} was read as "No plan" by the built-in (and the plugin), it is now unread; a moved Devin was listed twice, the built-in still finding the Devin CLI's own sign-in; and moving back left the plugin's rows in logins.json, listed as empty accounts. Checked in a sandbox HOME with real Command Code and Devin accounts moved onto the community plugins (0.1.1): GOAT, its period, 5 hours / Weekly / Credits for Command Code, Teams, balance and Daily/Weekly for Devin, the same on the built-in after moving back, no plugin rows left. TestPluginUsage, TestCommandCodeSubscriptionUnread and TestMove (the plugin's rows after moving back) fail without the change. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass (TestClaudeSignedOut and TestUserPath timed out once at load 22, pass alone). | ||
|
cyxer000
|
6035cf99c8 |
agents: omp keeps magpie while a fallback chain or another role is on it, and a provider renamed takes those along (#340)
omp names models beyond modelRoles.default: its other roles, retry.fallbackChains, enabledModels and task.agentModelOverrides. magpie looked only at modelRoles' scalar roles before dropping its provider from models.yml, and a rename moved only the default, so a chain on magpie/<p>/x:max was left pointing at a model omp no longer had, which it skips with a warning. |
||
|
cyxer000
|
b60cfa6787 |
agents: omp, Pi, Cline and dsh are no longer told a model writes more than its window holds (#338)
models.dev lists some models' output above their context (deepseek-chat: 384000 out, 128000 in), and magpie handed that on as maxTokens. The limit is now kept within the contextWindow written beside it; a model whose window isn't known keeps its output as before. Follow-up to the review of |
||
|
yetone
|
a9ff84fd80 | accounts: a Claude account's usage-limit resets show on its card, and can be used, by hand or by themselves (StringKe on Discord: claude-code usage 里有 reset) — magpie read Claude usage without the resets. It now asks as Claude Code does (/api/oauth/usage?cedar_ember=1&skip_spend=1) and shows ↺ N resets · until … on the card and panel. "Use a reset" spends the grant Anthropic names next through POST /api/organizations/{org}/reset_rate_limits, as Claude Code's /limit-reset does, the organization read from /api/oauth/profile; Auto-use (off by default, per account) spends one only when the account's whole week is used up, every other candidate is resting and the grant clears seven_day, at most one a week. The routing page labels an automatic one. Checked against fake servers with the user's JSON, never against Anthropic. TestClaudeGrants, TestClaudeResetsOnCard, TestUseClaudeReset, TestAutoUseClaudeReset, TestClaudeAutoReset and claude-resets.test.cjs (Chromium, WebKit, en/zh) fail without the change; codex-auto-reset, routing-auto-reset, click-scroll, old-webkit pass. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass. | ||
|
yetone
|
69b366adec | omp: each model is asked on its provider's own API (#329) — magpie wrote every model into omp's models.yml as openai-completions, so a Claude's thinking signatures had no place between tool turns. As for Pi, a Responses model now gets api: openai-responses and an Anthropic one api: anthropic-messages at the gateway's /v1/messages, thinking adaptively on Claude 4.6 and later, else on a budget (budget-effort would send output_config.effort, which Sonnet/Haiku 4.5 refuse); groups and the rest stay on Chat. A model offering max made omp 16.3.5 reject the whole file, so every magpie model vanished; max is now offered as xhigh, which the gateway fits to max. Checked with the real omp 16.3.5 in a sandbox HOME against a fake upstream: Claude → POST /v1/messages, deepseek → /v1/chat/completions. TestOmpModelsAskedOnTheirNativeAPI fails without the change; TestOmpMessagesRelayedAsSent guards the relay. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass. | ||
|
yetone
|
b03967bb79 | library: agents in a running WSL distro take skills, MCP servers and instructions (#331) — the Library knew only this machine's agent ids, so codex@wsl:Ubuntu and the like were never offered, and the id's colon was refused as an agent's name and can't be in a Windows file name. Claude Code, Codex, Pi and OmO in a distro now get them at their default places under the distro's $HOME through \\wsl.localhost, only while it runs (opening a stopped one's files starts it; its state is kept and asking for it says to start it). Skills go in as copies, made beside and renamed into place and made again when the library's changes, since a Linux agent can't follow a link to a Windows folder (project skills share the same copy code); an MCP server that runs a Windows program (C:\…, *.exe/.cmd/.bat/.ps1) is refused for them with a message; Pi there gets no MCP servers, where its version decides the file. The id's colon is a dot in file and folder names, and setup export/import turns it back. TestWSLTargets, TestWSLSkillsCopied, TestWSLServers and TestWSLInstructions (a fake distro) fail without the change. go vet (and GOOS=windows for agent, library), go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass. Not run against a real distro. | ||
|
cyxer000
|
007a84964a |
agents: omp takes magpie's vision models for text-only (#327)
magpie's models.yml entries had no input or maxTokens, so omp fell back to a fuzzy-matched bundled model or text-only / 16384. Write input from the model's image answer (omitted when unknown) and maxTokens from its output limit; carry ImageInput through magpieModels. |
||
|
yetone
|
ad90eced2b | claude: every 1M model magpie writes for Claude Code is marked [1m] (StringKe on Discord: Autocompact is thrashing on Opus 5.5 with a Max subscription) — Claude Code 2.1.284 and before takes any Claude model not named with [1m] for 200K, CLAUDE_CODE_MAX_CONTEXT_TOKENS or not (it applies that only to models it doesn't know), and compacts at 160–190K over and over; magpie marked only its picker's options, and only when it knew the window, so a model typed, or picked while the window wasn't known, went into ANTHROPIC_MODEL, model, every tier and CLAUDE_CODE_SUBAGENT_MODEL bare. Each is now marked when magpie's list or models.dev gives a window of 1M or more. Checked with /context and full sessions of 2.1.280–2.1.285 in a sandbox HOME: unmarked compacted 3 times at 190K, marked 0. TestClaude1MMarked fails without the change. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass. | ||
|
yetone
|
ed5b3da53a | library: an All chip gives an MCP server or skill to every agent at once (StringKe on Discord: 一个个点太麻烦) — each row of the Library now leads its agent chips with All: one click turns the item on for every agent that can take it (those with no MCP file, or no SSE for an SSE server, are skipped; agents hidden on the Agents page keep what they have), and once all have it a click takes it off all. It is one call to the same servers/agents or skills/agents endpoint as a single chip, so the row isn't redrawn and nothing scrolls; a partial failure says on how many it took and names the first refusal, and the refused chip carries its dot. Shown only where two or more agents can take the item. library-all.test.cjs (Chromium, WebKit, en/zh) fails 14/14 without the change. library-all, library-toggle-status, library-items, shared-skills, old-webkit, click-scroll pass (70); go test ./internal/gui passes. | ||
|
yetone
|
d1491a43e8 | gateway: X-Magpie-Account pins a request to one account of a subscription (gakki on Discord: 想单独测某个账号) — a subscription with several accounts took any of them in turn, so a probe of one account could be answered by another. The header (the account's email or login, or its id on the Routing page) narrows the request to that account alone: an unknown one is a 404 naming the accounts there are, one whose plan lacks the model a 400, one resting a 429 with until when, and nothing else is tried in its place (nor a Codex reset spent by itself). Pooled Codex accounts are pinned the same through /backend-api; the header is never sent on to the vendor, and the Routing page's trace records it. TestAccountPinned, TestAccountPinnedUnknown and TestAccountPinnedResting fail without the change. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass (TestClaudeAccountNamedAsItsLogin timed out once under load, passes alone). | ||
|
yetone
|
e92994b37a | agents, library: Antigravity alone no longer shows Gemini CLI (#330), and turning an agent off on a skill or MCP server says it was removed (#332) — Gemini CLI was found from ~/.gemini existing, where Antigravity keeps its own folders (antigravity, antigravity-cli, config) and reads GEMINI.md; it now takes only what Gemini CLI writes there (settings.json, .env, google_accounts.json, installation_id, trustedFolders.json, mcp-oauth-tokens.json, an oauth_creds.json its own OAuth client minted, as #143) or a gemini on PATH. The Library's agent chips said 「已写入 X」 on the way off too; they now say 「已从 X 中移除」 (or N agents, or N updated for a mix). TestGeminiNotAntigravity and library-toggle-status.test.cjs (Chromium, WebKit, en/zh) fail without the change. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass; library-items, shared-skills, click-scroll, old-webkit pass. | ||
|
yetone
|
d1ec1cdf62 | usage: a Codex account can spend one of its rate-limit resets by itself once its week is used up (StringKe on Discord: 账号里有 Bank Reset 的重置次数，可以自动使用 — 七天全部用完的时候重置) — off by default, turned on per account with Auto-use beside Use a reset (Usage page, panel) or magpie quota auto-reset <account> on. It fires only when every other account a request could go to is resting, fresh usage shows the weekly window used up (the 5 hours' being full never counts: a reset starts both, and five hours pass on their own), the account holds one, and none was spent by itself this week (kept in codex-autoreset.json across restarts); it spends the one expiring first, lifts the rest and asks once more, and on nothing_to_reset/no_credit/error ChatGPT's own 429 goes to the agent. Both the pooled accounts and Codex's own sign-in are covered; each use shows on the Routing page and in the request log. TestCodexAutoResetOneAccount, TestCodexAutoResetAfterEveryAccount, TestCodexAutoResetNot, TestWeekUsedUp, TestAutoResetKeptPastRestart, codex-auto-reset.test.cjs and routing-auto-reset.test.cjs are new; the gateway and GUI ones fail without the change. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass; click-scroll, old-webkit, tray-usages pass. | ||
|
yetone
|
3bec6c0e40 | providers: a built-in subscription moves onto its community plugin and back, its accounts with it (the user: 慢慢下掉内置的那些 Subscription Provider…不要让用户一升级完之后，突然发现他的所有服务都不可用了) — eleven built-ins (Zed, Qoder, Factory, MiMo, Devin, Grok, Command Code Plan, Cursor, Kiro, WorkBuddy, ZCode) each get a mover to their @magpie-community package. A move installs the plugin (updated when older than the mover needs), hands it every account in the plugin's shape, checks the plugin lists models for them, and only then lets the plugin serve the same provider id, so agents' model ids don't change; any failure rolls back and the built-in keeps serving. The built-in's accounts are kept as a backup, and "Run built-in again" (magpie plugin move-back <id>) takes the plugin's current sign-ins back, never copying a rotating token: they are taken out of the plugin in one step, and an account the built-in renewed meanwhile keeps its newer token. An account only the plugin can hold (Cursor's browser sign-in) stays with it. The provider editor shows "Runs on" with the button, a failed move's reason, and the CLI has magpie plugin move / move-back. Automatic moves (Retiring) are wired in but the list stays empty until the packages are on npm. Checked with real accounts in a sandbox HOME: Command Code Plan and Devin moved, answered a chat through the gateway on the plugin, moved back and answered again on the built-in. TestMove*, TestPutBackKeepsNewer, the movers' round-trip tests and plugin-move.test.cjs (Chromium, WebKit, en/zh) are new. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass; click-scroll, old-webkit pass. | ||
|
yetone
|
d1b6c119c7 | ci: the UI preview's planner uses deepseek-flash instead of deepseek-v4-pro (PLAN_MODEL still overrides) — asked for by the maintainer. Checked against DeepSeek's API: deepseek-flash answers the planner's JSON mode (response_format json_object) with a valid plan; it reasons first (~1k tokens on a small plan), well inside the planner's max_tokens 16000. | ||
|
yetone
|
eb3a0745e1 | gateway: a rate limit that counts tokens reaches the agent as a rate limit, not as "prompt is too long" (StringKe on Discord: Autocompact is thrashing, /goal stops as context limit reached) — tooLongRe's "too many tokens" also matched Bedrock's 429 "Too many tokens, please wait before trying again." and Cerebras's per-minute limit, so magpie told Claude Code its conversation no longer fit; Claude Code compacted, hit the limit again a turn later and compacted again, three times, then gave up as thrashing. A 429, or an error in rate wording (rate limit, per minute/hour/day, TPM/TPD, please wait, try again later, throttled), is now passed on as the limit it is. TestRateLimitNotContextOverflow and TestRateLimitReachesClaudeCodeAsRateLimit fail without the change. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass. | ||
|
yetone
|
52c8e838d2 | providers, sign-in, tray, plugins: four of StringKe's reports on Discord — (1) Removing a provider left its editor open and listed, and a second Remove said there was no such provider: the removal had been made, but moving the agents off its models failed on one agent whose config couldn't be written, and Reseat returned that as the change's error; now such an agent is a move with its error ("still on X, not moved: …", a warning in the panel, a line in the CLI and TUI), the others are moved, and the panel, told a delete failed, re-reads the list and closes the editor when the provider is gone. (2) The sign-in waiting sheet shows the sign-in link itself, selected whole on a click, with a copy button, for a browser other than the one that opens. (3) A subscription with several accounts offers "Account in use" among the menu bar's usages, following the account the gateway goes to first. (4) The Antigravity plugin's sign-in never started: magpie called every plugin's authorize with an inputs object, the way OpenCode's CLI does, and opencode-antigravity-auth then asked its Project ID on the terminal — magpie's stdin — until the minute ran out; inputs now go only to a method with prompts, as OpenCode's TUI passes them (checked against the real package under Bun in a sandbox: the Google sign-in URL comes back at once). TestReseatUnmovable, TestTrayInUse, TestInUseOf, TestAuthorizeNoPrompts, provider-remove.test.cjs, signin-link.test.cjs and tray-inuse.test.cjs fail without the change. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass; click-scroll, old-webkit, tray-usages, plugin-signin, signin-callback, factory-sub pass. | ||
|
Comic Chang
|
901ee08280 |
Count usage at the configured provider/model price (#278)
Magpie reports models.dev's list price for every call. That is the right number for a vendor's own key and the wrong one for a provider that resells or exposes a model at a different tariff, and it leaves a model the catalogue does not list with no cost at all — a provider's own /models gives ids, not economics. magpie model price relay-a/gpt-5.5 0.12,1.20,0.01,0.15 magpie model price relay-a/* 0.12,1.20,0.01,0.15 magpie model price relay-a/gpt-5.5 --reset magpie model prices Absolute USD per million tokens. All four parts are required: a price missing one would understate the rest of every call, and a hand-edited file that left a part out would bill it at zero, so each part is a pointer and the setter refuses a price that is negative, NaN or infinite, naming the part at fault. Zero stays distinct throughout — a model served at no cost has a price, not the absence of one. A `<provider>/*` entry covers every model of that provider and an exact entry wins over it; --reset removes only the exact entry and says so when a provider-wide one is still in force. The order a price is looked for in is the price for this model, then `<provider>/*`, then the provider's own catalogue, then models.dev for the maker. A price is a provider's tariff, not the model's: the same model through two providers has two prices, and each keeps its own. A provider is resolved by its id, or by an id it was renamed from, and never by its display name — Find answers those too, and a record naming one was counted at another provider's price. provider.EffectivePrice is the one lookup every cost caller shares, so the usage ledger and a session's totals both go through it, and a session naming a model bare is still priced at its maker's list price, which is a different question from what one provider charges. catalog.PriceOf and PricedBy keep returning the models.dev price for anything wanting an unbiased number. The background-task pickers (draw, search, vision) still rank by catalogue price: they choose which model answers, not what a call is reported to cost. Unlike every other per-model preference this does not call catalog.Touched. What a call costs is not what an agent picks a model by, and the model lists magpie keeps in the agents' own files are not its to rewrite over a number in a cost report. A rename moves the prices with it through the walk #288 adds, so nothing here has to say so, and an id recorded before a rename still resolves. Validation happens where the entry is written, not in Save: one hand-edited bad price in the file must not make saving a theme or a window size fail. A price for a model the provider does not serve is refused the way `magpie model name` refuses the same id, since it is a price that never applies and nothing reports it as dead; a removal is exempt, so an entry left for a model that has since gone can still be taken away. |
||
|
yetone
|
8124d3f927 | edit: a config kept as a symlink stays one when magpie saves or clears it (#323, jigaowan) — WriteAtomic wrote a temp file beside the path and renamed it over it, so a linked library.json, instructions.md, CLAUDE.md, settings.json or config.toml became a file of its own and the dotfiles target kept its old text; clearing instructions.md removed the link. Now a write goes to the file at the end of the links (the one it names when nothing is there yet, an error for a loop of links), keeping its mode, and clearing a linked file empties its target and keeps the link (Pi's migrated mcp.json stays as {}); a plain file is removed as before. Sign-ins and the Kiro/StepFun files magpie writes privately follow links the same way, and a failed edit rolled back deletes only what it made behind a link to nothing. TestWriteAtomicFollowsSymlink, TestRemoveKeepsSymlink, TestAtomicallyKeepsSymlink, TestLinkedFilesStayLinked and TestPrivateWritesKeepSymlink fail without the change. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass. | ||
|
yetone
|
1ba6939185 | agents: OpenChamber gets its own row, its model and small model set to magpie's (#321) — OpenChamber keeps its own default model (preferences.json, a copy in settings.json, under $OPENCHAMBER_DATA_DIR or ~/.config/openchamber) and sends it with every session over OpenCode's, so setting OpenCode's model changed nothing it used. Its row writes defaultModel (a fresh updatedAt, defaultVariant cleared as its own settings do) and the small-model override, keeping every other key and refusing a preferences.json it can't read; magpie's provider goes into the OpenCode config it runs on, and stays there while either uses it. OpenCode's config now follows $OPENCODE_CONFIG_DIR: the OpenCode 2 OpenChamber bundles reads only that folder, so what magpie wrote to ~/.config/opencode was never read; OpenCode 1 reads it last, so it wins there too. A project with its own model in OpenChamber is named in the row. Checked against @openchamber/web 2.0.4 on OpenCode 2.0.18 in a sandbox HOME: its settings API returned magpie's model and OpenCode listed magpie's provider. TestOpenCodeConfigDir, TestOpenChamberModel and TestOpenChamberSettingsOnly fail without the change. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass; click-scroll, old-webkit pass. | ||
|
yetone
|
953bce2cfb | agents: Codex signed in with only an API key gets magpie as its provider, its picker listing magpie's models (#322, dakango: switching the Codex app to one of its own models went to OpenAI, 502) — magpie counted an API key in auth.json as a ChatGPT sign-in and only set openai_base_url, counting on Codex to ask the gateway for its models; but Codex asks for none with an API key (models-manager refresh_available_models returns early), so the picker showed Codex's built-in models and the one magpie model, and a built-in one went to OpenAI with the relay's key. Now only a ChatGPT sign-in takes that route; with an API key alone magpie is the model_provider with model_catalog_json listing every magpie model on for Codex, as when signed out, and a sync moves a setup an older magpie wrote; going back to Codex's own model restores the user's model_provider. A Codex model whose OpenAI can't be reached now fails naming the model and what to do instead of a bare 502. TestCodexAPIKeyUsesProvider, TestCodexAPIKeyBaseURLMoved and TestCodexOwnModelUnreached fail without the change. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass. | ||
|
yetone
|
b63a0f1fd5 | plugins: a plugin's provider takes more than one account, as a built-in subscription does (the user: 插件当然要支持多账号了) — a plugin kept one sign-in per provider, and signing in again replaced it. Now each sign-in goes beside the others: plugin-auth.json keeps the first under the provider's id, as OpenCode does (so what is signed in already stays the first account), the rest under id#slot; logins.json lists them as it lists the built-ins' accounts, so the editor shows them all, one first, the others ticked on behind it or off, any made first, any removed (which signs it out). The host runs every request in its account's scope, so a plugin's getAuth, client.auth.set (a refreshed token), loader and provider.models see that account alone; a sign-in to an account already there (the same id, else the same secret) replaces that one's rather than listing it twice. The gateway spreads and fails over across the accounts on, as for the built-ins. Accounts with no id are told apart by the end of their key ("API key …abcd"), else by their slot. Also on the Devin page: the header shows the plugin's icon, and Cognition's opencode-devin is off the market (its gateway answers 404 model_not_found for models and chat). TestPluginAccounts (plugin: per-account requests and refreshes, dedupe, sign-out; provider: first, on/off, switch, forget, labels), TestPluginProvider (gateway: a 429 on the first account goes on the second) and plugin-signin.test.cjs (add a second account in the editor, make it first; fails without the change) are new. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass; plugin-signin, plugin-market, old-webkit, click-scroll pass. | ||
|
yetone
|
ef4edf8c58 | tray: the menu bar shows several subscriptions' usage side by side (KevinXC on Discord) — Settings → Usage in the menu bar picked one card; its menu now ticks any number (kept open while ticking, saved once when it closes, Off unticks all, a ticked card that has gone stays listed to untick) and the pill says "3 subscriptions". settings.TrayUsages keeps them in order; a file with only the older trayUsage shows that one, and trayUsage is still written as the first for an older magpie. On the Mac the bird and a cell per card are drawn as one image by AppKit on the status item's button: the card's logo (a black glyph tinted in the menu bar's text colour, a coloured one as it is, the name's letter in a ring when there is none) and its two windows stacked, "42%" over "18%", in the bar's colour light or dark and sharp at any scale; the bird's flap goes through it. Arc flags run into numbers (Codex's logo) are spaced out for AppKit's SVG reader. A row longer than 10 characters (a plan's balance read from its page) is cut with an ellipsis in the bar and whole in the tooltip. Windows and Linux show the cards as text, " | " between them. TestTrayUsageCells, TestSVGArcFlags, TestTrayImage (darwin, renders 0-3 cards light and dark at 2x), TestTrayUsagesMigrate and tray-usages.test.cjs (Chromium, WebKit, en/zh) are new. go vet, go build (darwin GUI), go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./..., go test ./internal/gui pass; tray-usages, settings-groups, panel-*, click-scroll, old-webkit pass. Not seen in a live menu bar. | ||
|
yetone
|
80737be8d7 | gateway: a vendor's Responses API gets Codex's request as Codex sends it to a provider not OpenAI's (#292, @byhooi: Anyrouter's gpt-6-astra answered "invalid codex request" through magpie, and through CC Switch too with its remote compaction on) — Codex decides by its provider's name alone (is_openai: name == "OpenAI") whether to send what only OpenAI takes: each message's internal_chat_message_metadata_passthrough (content_item_kinds, turn_id), a call's encrypted_function_args, stream_options.reasoning_summary_delivery, configuration_update items. CC Switch's remote compaction switch is that name; signed in, Codex keeps its built-in provider, named OpenAI, and comes through openai_base_url, so every request magpie relayed carried them, and a relay that checks it is Codex's turned it away. A relayed Responses request to anyone but OpenAI's API and the ChatGPT backend now goes without them, as Codex itself leaves them out under another name; everything else as it came, byte for byte when none is in it (another client's stream_options stay). Codex's prompts and identity untouched. TestCodexOpenAIFieldsStayWithOpenAI fails without the change (the relay's 400 "invalid codex request"). go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass. | ||
|
yetone
|
52a0d799d6 |
routing: a group can be routed by hand, its model picked on its card (#317, @azir12345: pick the channel as CC Switch does) — a group's routing may now be Manual: every request goes to the one member picked (pick in the group's JSON; the first when none or one no longer in it), over that member's own accounts or keys, and the others and the rules wait (kept, not dropped) until another routing is chosen; none takes over when it fails. On Routing, a manual group's card lists its models as pills, the picked one marked by a dot (role radio), and clicking another saves the group with that pick without opening its editor or moving the page; its rules tag says they wait. The editor offers Manual beside the other routings. magpie group pick <id> <model> (or group set <id> pick=<model>, a bare model id when it names one member) picks from the CLI; magpie groups and group show mark the pick, the TUI shows "manual → model". A renamed provider or model renames the pick. TestManualGroup, TestGroupPick and routing-manual.test.cjs (Chromium, WebKit, en/zh) fail without the change. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass; click-scroll, old-webkit, routing-levels, routing-steady, panel-routing, settings-groups pass.
|
||
|
yetone
|
d08018e433 | gateway: a gpt-6.x refusal after the ChatGPT backend's safety buffering goes on to the next account, and a refusal tries the same model's other accounts first (#248, Koohoko) — the backend's response.metadata event (safety_buffering, moderation metadata) was taken for the reply's content and let the stream through, so the response.failed bio_policy after it reached Codex as a 200 ("This content can't be shown") with nobody else asked; it is now a lead, and a stream the backend said it holds back for safety checks is held up to 4 minutes rather than 15s (gpt-6.1-sol at xhigh said nothing for 35s). A turn kept on the account that answered it had that account alone first and its member's other accounts where the member sits in the group, so a refusal went to the group's first member (Sonnet); the refused model's other keys or accounts that aren't resting now go next. TestRefusalAfterResponseMetadataMovesToNextAccount, TestSafetyBufferedStreamHeldLonger and TestRefusalTriesTheModelsOtherAccountFirst fail without the change. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass. | ||
|
yetone
|
8bf7390584 | copilot: Auto asks its session with the API version VS Code sends, and an account Copilot has no Auto for is told so (#256, CakewthinSUm: "Copilot Auto: 404 Not Found") — signed in from magpie (the editors' sign-in), the POST {api}/models/session went out with no X-GitHub-Api-Version, which VS Code's Copilot Chat puts on every CAPI request (@vscode/copilot-api 0.2.19 _mixinHeaders: 2025-10-01, AutoModels among the types); it now carries 2025-10-01 (the Copilot CLI's sign-in keeps its own 2026-07-01). VS Code's session answer names no selected_model, only available_models, and it takes the first it knows: magpie does the same when none is named. A 404 however asked falls back to the first model the account may pick by hand, sent without a session, for 10 minutes; with none, the error says Copilot doesn't offer Auto to this account. TestCopilotAutoSessionAsVSCode and TestCopilotAutoUnavailable fail without the change. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass. | ||
|
yetone
|
68f9daa4fa | library: an agent's own copy of a library skill gives way to it, and one that differs is settled from the warning (StringKe, JasonLeeForOnly on Discord: after Bring in all, "Claude Code already has a skill of its own called impeccable", 这里没有强制覆盖的能力) — a skill is brought in from the agent with the very folder and given to the agents that had that folder; another agent's copy (CC Switch copies a skill into each agent) was listed as "differs in" and left out, and giving the skill to it, or a copy put back into an agent after its folder became magpie's link (by CC Switch or whatever installed it), was a hard failure with no way out. A folder there holding the same files as the library's (bytes compared; .DS_Store, .git and magpie's copy mark aside) is now set aside into backups/<when>/<agent>/skills and the library's linked in its place; a skill brought in takes the agents with such a copy too, which are no longer said to differ; a move that copied it all but couldn't remove the folder brings it in all the same, what was left set aside. One that differs keeps the warning, now in the reader's language with "Use the library's" (the agent's set aside, the library's linked) and "Keep <agent>'s" (the agent, and any reading the same folder, taken off the skill) on its row — skills/use-library and skills/keep-own, magpie library skill use-library|keep-own <name> <agent>, which the CLI suggests under the problem. Backups holding a skill set aside are never pruned. TestOwnSkillInTheWay, TestSameTree, TestPruneKeepsSkillsSetAside and own-skill.test.cjs (Chromium, WebKit, en/zh) fail without the change; TestSharedAgentsSkills now expects the byte copy to be the library's. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass; own-skill, import-all-skills, library-items, shared-skills, market-have, click-scroll, old-webkit pass. | ||
|
yetone
|
7926dcc226 | gui: a plugin's sign-in picker keeps its question readable, and a plugin's provider shows its vendor's icon (the user: 这个 UI 为啥这样 / 这里必须要有真实 icon) — Devin's plugin names its ways long ("Paste an existing Devin session token…"), and the buttons, kept on one line beside the question, pushed it into a column a character wide and ran off the sheet; the ways now wrap under the question, each wrapping its own label. A plugin's provider showed a plain box for any vendor outside OpenCode's few; it now takes the icon the plugin market lists for its package, else for a listed plugin of the same provider (Devin, Zed, Kiro…), read from the list fetched last, the cached copy or the built-in one, never the network. TestMarketIcon and plugin-signin.test.cjs (question squeezed to 12% of the box) fail without the change. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./internal/plugin ./internal/gui ./internal/provider pass; plugin-signin, plugin-market, old-webkit, click-scroll pass. |