yetone
f22218a092
gui: after an update the window shows what changed since the version last run (a Discord user: 点更新后能弹个窗显示更新了啥吗, to see whether their issue was fixed) — magpie updated itself silently, and its release notes were only on GitHub. The version last run is now kept in magpie's own folder (last-version); started on a newer release, the window or magpie web's page asks usemagpie.ai's new /api/notes (beside /api/latest; site/worker.js lists the releases' notes from GitHub, cached as the feed is) for every release since, newest first, without their Install section, and shows them once in a What's new dialog. A fresh install, the same version, a downgrade or a build from source shows nothing; a magpie from before the version was kept, already in use, shows its own version's notes; offline nothing is shown and nothing waits on it; until the site is deployed, the update feed's newest notes stand in when they are the current version's. The tray's panel shows no dialog. The notes are drawn as text, never as HTML: headings, bullets, bold, code, http(s) links, and #NNN links to the issue, opened in the browser as the app's other links are. Settings has a What's new row under Version that opens them again, with a waiting update's notes first, marked Not installed yet; /api/update's notes leave out the Install section too. TestShowNotes, TestStripInstall, TestBetween, TestNotesBetween, TestWhatsNewAfterUpgrade, TestWhatsNewFromBefore, TestUpdateNotesWithoutInstall and whats-new.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, update-check, update-hide pass.
2026-10-02 03:57:55 +08:00
yetone
23472507c0
agents: Muse Code, Meta's muse CLI, is an agent magpie sets up (Discord: Muse Code 能加进来吗) — magpie points its endpoint_transport (~/.config/muse/settings.json, $XDG_CONFIG_HOME) at the gateway with auth "none", so the Meta sign-in's token is neither read nor sent, and sets its model to the catalog id; the endpoint and model the user had are stashed and put back on reset, the file's other keys (mcpServers, tui, proxy…) kept, and a settings file magpie had to make (with the schema_version Muse refuses one without) goes again. Muse lists its models from /muse-code/models on its endpoint's host before every session and starts none without it, so the gateway now serves that list, each row with the metadata["muse-code"] Muse shows and a limit with both window and reply size (one without either is hidden; none has it ask for 128K-token replies). A Responses stream the gateway translates from another API started with output null, which Muse reads as a broken stream and retries ten times; it is an empty list, as OpenAI's is. Its requests (muse-build/…) count under Muse Code in usage; Meta's icon from dev.meta.ai. Checked with muse 1.4.2 in a sandbox HOME against a sandbox gateway: exec answered through a Responses fake and through a chat fake (25 tools flattened, a read_file round trip), and switching back left settings.json byte-identical, or removed the one magpie made. TestMuse, TestMuseNoSettings, TestMuseModels and TestResponsesStartOutputList fail without the change (TestDriftUnwiredEveryAgent covers it too). go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass (TestSavedButSignedOutClaudeSaysWhy flaked once, passes alone); click-scroll, old-webkit pass.
2026-10-01 14:23:04 +08:00
yetone
04805abf39
agent: MiniMax Code ( #362 ) — MiniMax's mcode CLI (and its desktop app, same runtime) reads $MINIMAX_DATA_DIR/config.yaml, else ~/.minimax/config.yaml. Choosing a magpie model adds custom_provider.magpie there (the gateway, spoken to as Anthropic messages, with the catalog's models, efforts, limits and image support) and sets defaultModel to custom_provider:magpie/<model>; the user's own default and variant are kept and put back on reset, their comments, providers and keys on magpie's entry stay, and an emptied custom_provider goes. The Library installs skills into its skills folder; it reads no user-wide MCP file, so it gets no MCP target. Checked against @minimax-ai/code 0.5.10 in a sandbox HOME: mcode provider list shows magpie's entry and mcode exec reaches a fake upstream through it with magpie's key, model and effort; after a reset it loads the restored file. TestMiniMaxCode, TestMiniMaxCodeSync, TestMiniMaxCodeLeavesNoEmptyProviders, TestMiniMaxCodeDataDir and TestMiniMaxCodeSkills fail without the change. go vet, go build -tags nogui (darwin, GOOS=linux), GOOS=windows go build, go test -tags nogui ./... pass (TestUserPath and the Claude account tests pass alone).
2026-10-01 03:24:34 +08:00
yetone
04f374fa8c
agent: OmO (oh-my-openagent, omo-ai), a fork of Pi that keeps its own ~/.omo/agent, gets its own row: a magpie model sets settings.json's defaultProvider/defaultModel and magpie's provider in models.json there as Pi's does, $OMO_CODING_AGENT_DIR / $SENPI_CODING_AGENT_DIR are honoured, the Library writes its AGENTS.md, mcp.json and skills, and omo update updates it ( #264 rhyme227). Pi's own ~/.pi is left alone. piIn becomes piLike(at, id, name, dir) so both share one wiring. Tested with omo_test.go in agent and library (fail without the change); go vet, go build -tags nogui (darwin, GOOS=linux, GOOS=windows), go test -tags nogui ./... pass.
2026-09-30 11:38:07 +08:00
yetone
3fe2ff9958
rules: a routing group's rule can be for the agent compacting its conversation, so a cheaper, faster model writes the summary while the conversation stays on its own (X, MR.Guo: 希望 Magpie 能像 OpenCode 一样支持单独指定 context compression model：当 Agent 需要做上下文压缩时…指定一个更便宜、更快的小模型专门负责总结和压缩历史上下文) — a compaction went to whatever model the conversation was on, the priciest in the group as often as not, and a long session paid for each summary at that price. A rule's new condition, compact (provider.Rule.Compact, "compacting"; magpie group rule add <group> use=<model> compact, compact=yes|no; the GUI editor's 压缩上下文时 / compacting toggle; the TUI hint), matches a request that is an agent compacting, told from the agent's own prompt (internal/gateway/compacting.go, read from each one's release): the system prompt of Claude Code 2.1's /compact and auto-compact, OpenCode's compaction agent, Pi, Gemini CLI's state_snapshot and Qwen Code, or the last user message of Claude Code's, Codex's (and magpie's own for a Codex compaction_trigger) and Kimi Code's; a prompt only quoted earlier in a conversation doesn't count. Only in a group with such a rule is a request looked at this way, so nothing else changes. A compaction is decided on its own, never held by the turn's rule, its classifier never asked; it isn't remembered for the turn, and neither the conversation's affinity nor the turn's size is taken from its answer, so the requests after it go on on the model the turn was on and its cache (without that, the next request of a Claude Code turn followed the summary to the cheap model). A member whose context is less than the compaction is passed over for the next rule that matches, or the group's order (RuleHit.Small). The trace tells it ("The agent is compacting the conversation, so rule 1 sends the summary to …", the models passed over named), and the editor notes a compact rule's model taking less than another member. Docs: start#rules (en, zh). Tested: internal/gateway/compacting_test.go — each agent's prompt taken, a plain and a quoted one not; in a group with rules compact→a/small and tokens≥2000→b/big, a long Claude Code turn on b, its /compact to a (Compact, N=1), the turn's next request back on b held, Codex's compaction to a too; a 70k-token compaction skipping a (64k) for rule 2 with Small [a/small]; a group with no compact rule routing a compaction as before; ParseRule/Line/Conditions/Matches for compact. TestRuleCompact failed with the affinity kept from the summary. internal/gui/tests/routing-compact.test.cjs, Chromium and WebKit, en and zh: the compaction in the trace, the rule's words, the toggle on and off with nothing moved, the room note, a compacting-only rule saved as compact:true and not refused. routing-kind/served/signin/steady, click-scroll and old-webkit pass. go vet, go build -tags nogui (and GOOS=linux, GOOS=windows) and go test -tags nogui ./... pass. Not tried against real agents' compactions through the gateway (the prompts are matched as read from their releases) nor in the real Wails window.
2026-09-30 10:24:18 +08:00
yetone
cb65895ac3
agents: Factory's Droid CLI is an agent magpie sets up ( #242 tasselx) — droid keeps its settings in ~/.factory/settings.json ($FACTORY_HOME_OVERRIDE/.factory when set), its BYOK models the customModels array ({model, displayName, baseUrl, apiKey, provider "anthropic" | "openai" (Responses) | "generic-chat-completion-api", maxOutputTokens, noImageSupport …}), picked as "custom:<id>". Picking a catalog model through magpie appends one entry per catalog model after the user's own (so their ids never move), each with an explicit id "custom:magpie/<provider>/<model>", the catalog's label as displayName, the gateway and token magpie, its context (maxContextLimit) and output when known, noImageSupport always written (droid takes a Chat Completions model as blind otherwise), and the API its provider speaks natively so the gateway relays it as it is: Responses → "openai" at /v1, Messages → "anthropic" at the gateway root (Anthropic's SDK adds /v1), anything else "generic-chat-completion-api" at /v1; and sets sessionDefaultSettings.model. The model shows in magpie as magpie/<ref>; the user's sessionDefaultSettings.model is stashed and put back on reset (a top-level "model", the docs' spelling, is left alone and is what droid falls back to), magpie's entries go and an emptied customModels or sessionDefaultSettings with them; everything else in the file, the user's entries included, is kept byte for byte. The picker offers the user's own custom models by the id droid gives them (its "id", else the displayName with whitespace as dashes and a count of the same name before it), including the legacy ~/.factory/config.json custom_models, which magpie never writes. Sync rewrites magpie's entries as providers change; Check reports a missing entry or a changed baseUrl/apiKey; its requests are Droid's in usage (User-Agent factory-cli/<version>). Icon is Factory's own favicon glyph (factory.ai/favicon.svg); lobehub has none. From the docs: docs.factory.ai/cli/byok/overview (customModels fields, the three providers, config.json legacy snake_case merged under settings.json), /cli/configuration/settings (model, sessionDefaultSettings.*), /droid-exec/overview (custom:<Display-Name>-<index>). Verified by reading the shipped droid 0.229.0 bundle (@factory/cli-linux-x64, unpacked, never installed or run): the zod schema of an entry (also id, index, maxContextLimit, enableThinking, reasoningEffort, bedrock-converse), ids as custom:${displayName.trim().replace(/\s+/g,"-")}-${n} with n counting equal names, an entry's own id winning, the lookup by id, top-level model/reasoningEffort/specModeModel moved into sessionDefaultSettings only when unset there, getModel reading sessionDefaultSettings.model, noImageSupport defaulting by provider, FACTORY_HOME_OVERRIDE, and BYOK requests carrying factory-cli/<version>. Tested in a sandbox HOME (internal/agent/droid_test.go): set/sync/reset on a settings.json as droid leaves it with a Groq BYOK model (its entry byte-identical, the file restored exactly), each protocol's provider and baseUrl, a moved baseUrl caught by Check and healed by Sync, picking the user's own model while on magpie's, no file at all, a top-level model, FACTORY_HOME_OVERRIDE and legacy config.json ids (custom:Local-Qwen-0/-1) offered and never written. go build -tags nogui (and GOOS=linux, GOOS=windows) and go test -tags nogui ./... pass (TestClaudeSignedOut and TestClaudeAccountNamedAsItsLogin flaked under load and pass alone). Not tried with a real droid: whether droid's /model lists the entries, that it reaches the gateway on each protocol, and how it sends thinking for a custom model (magpie sets no reasoningEffort/enableThinking) are unverified.
2026-09-30 02:35:59 +08:00
yetone
b881932ec2
gui: the page runs in macOS 12's WebKit — no regex lookbehind, the few newer built-ins filled in, fallbacks for container queries, subgrid, :has and color-mix ( #220 uclort: on macOS 12.7.6 the app opened blank, the panel showing its tab bar, a "Profiles + Save current" heading and "Open magpie · Quit" and nothing else, no button working) — the page runs in the system's WebKit, on macOS 12 Safari 15.x's, and app.js's snippet highlighter had a regex lookbehind, (?<==)\S+ (app.js:2167), which WebKit only parses from Safari 16.4: a SyntaxError in a literal fails the whole file, so app.js never ran (and routing.js and library.js, which lean on it, threw), leaving index.html's static markup; library.js had two more, (?<![\w-]) in the SVG greying (library.js:162-163). The highlighter now finds a value after "=" by hand (the character before the match, a sticky \S+) and the greying checks the character before a colour name in its replace callback, each giving the same output as before (compared on shell, curl, Python and Node snippets and an SVG with attribute and style colours, data-fill and x-color left alone). Built-ins newer than Safari 15.0 in use, routing.js:307's findLast and library.js:1042's structuredClone (15.4), are filled in by a new compat.js loaded before the other scripts (with at, findLastIndex and Object.hasOwn), each only where missing; structuredClone there is a JSON copy, enough for the API's plain data. Styles: a selector list with :focus-visible (15.4) drops the whole rule before 15.4, so the agent handle's hover, an account's Remove and protocol buttons showing on hover, the protocol menu's hover and the editor's focus ring are split from their :focus-visible (or it is dropped where :focus covers it); .acc:has(.aq) and the panel's .profiles:has(> .chip-input) hint (15.4) are classes set by app.js (with-aq, naming); the Routing page's container queries and the request list's subgrid (16) get @supports not fallbacks by the window's width (the tray panel is narrower than all of them) and a row's own columns; and the panel's --panel-tint, a color-mix() (16.2) in a custom property that would have gone invalid and painted the panel clear (tintPanel then handing the system white under dark text), falls back to --bg, as the floating status and Library's sticky head do. Other things newer than 15.0 are left as cosmetic: inert (15.5) on the folded agent list, accent-color, the rest of color-mix() on hover and focus shades, .quota's subgrid rows. The build: Go 1.25 and later run on macOS 12 and up only (the linker stamps 12.0 as the oldest), so Info.plist's LSMinimumSystemVersion and the Makefile's -mmacosx-version-min go from 11.0 to 12.0 and the site says macOS 12+ rather than 11+. Tested with a new internal/gui/tests/old-webkit.test.cjs: every assets/*.js parsed with the Babel parser Playwright bundles, failing on a regex lookbehind, v flag or modifiers (in a literal or new RegExp("…")), a class static block, decorators, import attributes or using (checked against the old highlighter's regex and a static block, and not on named groups, lookahead, ??= or private methods); a grep for built-ins newer than 15.0 (at, findLast, structuredClone, hasOwn, toSorted and co., Set methods, groupBy, withResolvers, Iterator helpers, popover …) unless compat.js fills them in (fails on main's routing.js:307 and library.js:1042 without it); compat.js the first of the page's scripts and every script loaded; the CSS with no :has(), no :focus-visible in a mixed list, no nesting or dvh, and @container, subgrid columns and a color-mix() custom property only with an @supports not fallback in the same file; and, in WebKit with those built-ins deleted, the panel's tabs, Save current's name field and every window page drawn with no page error. Documented in internal/gui/tests/README.md. go build -tags nogui (and GOOS=linux, GOOS=windows), go build (darwin GUI), go test -tags nogui ./... and the whole GUI suite (130 tests) pass. Not tried on a real macOS 12 or Safari 15: the old engine's parse is judged by the parser, not run.
2026-09-29 23:52:38 +08:00
Austie
86a2b8cf47
providers: qianfan personal, team and pay-as-you-go endpoints ( #211 )
...
* providers: qianfan personal, team and pay-as-you-go endpoints as its preset regions
* providers: qianfan review fixes — pay-as-you-go fetches /v2/models, enterprise naming, the plans' union models, a zh note
* providers: qianfan plans list nothing, pay as you go does — NoList scoped by region
* providers: qianfan review round two — old id maps to the new preset, the union models, IAM keys and a README section
* providers: qianfan key link follows the region — normalize takes it from the endpoints, the button from the plan picked
* providers: ParseImport takes a region key page
2026-09-29 23:25:56 +08:00
yetone
30300c40d0
providers: NVIDIA and ModelScope are presets ( #197 : 增加 NVIDIA NIM 和魔搭 ModelScope 作为供应商预设) — NVIDIA NIM at integrate.api.nvidia.com/v1 with a key from build.nvidia.com, and 魔搭's API-Inference at api-inference.modelscope.cn/v1 with a ModelScope access token (not DashScope, which the Qwen presets are), each with its models.dev catalog (nvidia, modelscope) and its logo. NVIDIA's /v1/responses answers 404 for its models but a few, so it has chat completions only; ModelScope's /v1/responses is served (401 without a token, 404 for a path it doesn't know), so it has both. Neither has an Anthropic endpoint here. An entry imported at either base URL is the preset, and the import link pages and README list them. Tested: the presets' endpoints, catalogs and import, a /v1/models answer shaped as each sends it (NVIDIA's embedding models left out, ModelScope's object "" rows kept), and catalog.FetchAt against the live integrate.api.nvidia.com (74 models) and api-inference.modelscope.cn (35) lists
2026-09-29 16:40:02 +08:00
yetone
e4404dbd6b
agents: Kimi Code, Moonshot's kimi CLI, is an agent magpie sets up (agent求个kimi code支持) — it keeps its settings in ~/.kimi/config.toml ($KIMI_SHARE_DIR's), its default_model a key of its [models."…"] tables, each naming a [providers.…] one. Picking a model through magpie adds the provider "magpie" (the gateway, as Kimi's own chat completions type, so the thinking goes out as reasoning_effort and comes back, and is sent back, as reasoning_content) and a table per catalog model keyed "magpie/<provider>/<model>", with its context (128K when not known) and thinking/image_in capabilities, so the catalog is in Kimi's /model picker and kept up to date as providers change; the Kimi Code sign-in's default is stashed and put back on reset, and the tables go in and out in the order Kimi's own check wants (a default or a provider it can't find makes it refuse the file). Its requests are Kimi Code's in usage (KimiCLI/…). The gateway also drops Kimi's thinking: {type: …} on a request relayed to api.openai.com, as it does Qwen's enable_thinking. Tested: the config in the shape a Kimi Code sign-in leaves it (set, sync, a moved base_url, reset, its own model, no config at all), and the real kimi 1.24.0 --print against a sandbox gateway and a fake upstream: reply and thinking shown, reasoning_effort high on a thinking model, reasoning_content sent back on the next turn, usage under Kimi Code; not with a real vendor behind it
2026-09-29 16:36:35 +08:00
Austie
6ba83dbbbb
providers: add the Baidu Qianfan Token Plan (个人版) preset ( #193 )
2026-09-29 14:37:24 +08:00
yetone
5910bdada5
docs: Get started says agents, not coding agents (把文案里的Coding agents统一改成agents) — magpie chooses the model for any agent, not only coding ones; the English lede said "each of your coding agents" and the Chinese one "编程 Agent"; both now just agents, as the home page already does
2026-09-29 01:45:47 +08:00
yetone
4150dfc079
provider: Volcengine Ark (火山方舟) is a preset, its Coding Plan, Agent Plan and pay-as-you-go (tcdw: 提供一个选项能够取消自动给 LLM 提供商地址补全 /v1/ 的默认行为) — volcengine, a first-party vendor with a Plan picker: Coding Plan (default) at https://ark.cn-beijing.volces.com/api/coding/v3 for chat completions and Responses and /api/coding for messages (套餐概览 docs/82379/1925114, 快速开始 1928261; its Codex page 2556056 sets wire_api "responses"); Agent Plan, which tcdw is on, at /api/plan/v3 (chat completions and Responses, its Hermes Agent page 2373743) and /api/plan (其他工具 2373746, Claude Code 2373740), with a key of its own; pay-as-you-go at /api/v3 (兼容 OpenAI SDK 1330626, 创建 Response 1569618), which both plans' pages warn bills apart from the plan — no Anthropic endpoint is documented for it. Its models (ark-code-latest, whichever the console picked, then doubao-seed-evolving, doubao-seed-2.1-pro/-lite, doubao-seed-2.0-mini, minimax-m3, glm-5.3, glm-5.3-flash, deepseek-v4.1-flash, deepseek-v4-flash, deepseek-v4-pro, kimi-k2.7-code, kimi-k2.8-preview, kimi-k3, lowercase as the quick-start page gives them) are shown until a list is fetched; no models.dev catalog is tied to it, as its volcengine one has pay-as-you-go's dated ids and volcengine-coding-plan misses the Agent Plan's. Key from ark.volcengine.com/region:cn-beijing/apikey. Their versioned paths go out as written (previous commit). Icon is lobehub's volcengine-color, as the others are; the import page offers its three plans
2026-09-29 01:19:06 +08:00
yetone
841855ca5a
provider: Huawei Cloud's MaaS Token Plan is a preset (Lemon: 能否支持华为 codearts 订阅啊) — huaweicloud, Huawei Cloud MaaS: the Token Plan (personal accounts, 西南-贵阳一 only) is spent only at its own endpoints, https://api.modelarts-maas.com/plan/v2 for chat completions (its OpenClaw, Cherry Studio and CodeArts pages, tokenplan-maas-0004/0009/0014) and /plan/anthropic for messages (its Claude Code page, tokenplan-maas-0003); pay-as-you-go MaaS is the other Plan, /openai/v1 (qs-maas-0001, OpenCode page maas-modelarts-0909) and /anthropic (model-call-060). No Responses on either. Its models (glm-5.3, glm-5.1, kimi-k2.6, deepseek-v4.1-flash, deepseek-v4-flash, lowercase as its OpenClaw page has them) are given until a list is fetched; the key is a MaaS API key from console.huaweicloud.com/modelarts/?#/model-studio/authmanage; no usage API is documented (quota is shown in the console's 订阅管理), so none is read. CodeArts (码道) itself isn't a provider: it has no official API, its private endpoints are reverse-engineered, and its own doc has it reach the Token Plan through these same endpoints. Icon is lobehub's huaweicloud-color, as the others are.
2026-09-29 00:22:50 +08:00
yetone
29c706d1e7
provider: Tencent Cloud Token Plan is a preset — TokenHub's coding subscription (its general and Hy plans on one sk-tp- key, from console.cloud.tencent.com/tokenhub/tokenplan), served at its own endpoints under api.lkeap.cloud.tencent.com/plan: v3 for chat completions and anthropic for messages, no Responses (its Codex page asks for wire_api chat); models.dev lists only its Hy models, so the preset gives the plan's (tc-code-latest, GLM 5–5.3, Kimi K3 and K2.7 Code, DeepSeek V4, MiniMax M3 and M2.7, hy4-preview, hy3) until the plan's own list is fetched, and an entry imported at those endpoints is the preset
2026-09-28 15:41:57 +08:00
yetone
31169a17f6
agent: fx (fx.sh, Vercel Labs' coding agent) — its model picked in magpie like any agent's; a model through magpie adds magpie to ~/.fx/settings.json as a keyless provider of fx's own (openai-chat-completions at the gateway, auth none) with the catalog as its model_metadata, the model in use first so fx's 256-model limit never cuts it, and sets provider magpie and models.magpie; its own models stay as they are, and default takes magpie's entry out. fx sends no effort to such a provider, so there is none to pick. Tested live from a sandbox: fx 0.0.11 listed magpie's models and read and wrote files through several tool rounds on DeepSeek
2026-09-28 11:17:20 +08:00
yetone
6c9a0aa4d7
agents: OpenHanako — magpie is a provider there, chat completions at the gateway's /v1 under the key magpie-hanako with every model it serves, their windows, output, images and reasoning said; picking one makes it the primary agent's chat model, and default puts back the one it had and removes the provider, marked deleted as OpenHanako marks one it removes. While OpenHanako runs it goes through its local API (server-info.json's port and token), which reloads at once; otherwise into provider-catalog.json and agents/<id>/config.yaml for its next start. Asked on Discord; checked with OpenHanako's own provider registry and model manager, which list magpie's models and resolve the chat model to the gateway
2026-09-28 01:12:46 +08:00
smallnest
03a01a548d
agent: MiMo Code — Xiaomi's fork of OpenCode, sharing its config shape ( #98 )
...
* agent: MiMo Code — a terminal coding assistant that is Xiaomi's fork of OpenCode, whose config keeps OpenCode's shape: its own mimocode.json(c) under ~/.config/mimocode, its auth beside it, and a magpie provider block with npm/@ai-sdk/openai-compatible, model and small_model fields. opencode() becomes openCodeLike() for the two to share it, and magpieProviderJSON splits shape from the catalog id (magpieProviderJSONFor), so a visibility narrowed on mimocode (magpie visible mimocode …) narrows its list and leaves OpenCode's alone. The library gives it the same instructions, MCP servers (its mcp key) and skills as OpenCode, except the shared skills go into its own skills/ folder: it reads Claude Code's skills only behind a flag, though it reads its CLAUDE.md like OpenCode, and the page says so. Its requests are told by the mimocode/ User-Agent. Checked against XiaomiMiMo/MiMo-Code
* icon: MiMo Code's own favicon, from packages/ui/src/assets/favicon — its frame with the bottom bar, in the monochrome the app masks to the text colour
2026-09-27 08:42:44 +08:00
yetone
7a3c434610
agents: Alma — magpie wires it through Alma's local API (localhost:23001, while Alma runs): choosing one of magpie's models for Alma adds a provider named magpie there (OpenAI type, the gateway's /v1, key magpie), offers magpie's models in it and makes the model Alma's default chat model, the rest of Alma's settings and its other providers left as they are; the list is kept current as magpie's catalog changes, and going back to Alma's own takes magpie's provider out. Asked on Discord
2026-09-26 19:18:51 +08:00
yetone
d4135b55e1
group: a routing group's models can be another group — group/<id> as a member, routed in its place by its own routing and rules, so Coder can be deepseek-v4-pro then Fast, a Coder rule can send a turn to group/fast and Fast's own rules pick within it; a group can't be in itself directly or through another (refused on save, left out of the picker), groups go at most 8 deep, and one can't be removed while another has it. The Routing tab shows a group in a group as a heading with its models under it, the packet going through it, and the log says what each group's rules and classifier decided
2026-09-26 13:41:17 +08:00
yetone
90ed57f077
docs: intent routing shows a real request in the Routing tab — a message asking for tests, told "writing or fixing tests" by deepseek-flash in 964 ms, goes to glm-5.3 by rule 2; light and dark, English and Chinese
2026-09-26 13:08:47 +08:00
yetone
f64d2fbaf0
intent: a reasoning classifier answered nothing now and then, and the turn after it wasn't classified — tested for real (20 coding messages, real models through magpie), deepseek-flash spent its 512 tokens thinking and answered "", and that 30 s rest skipped the next turn too; the classifier is now asked for its least reasoning (none, else its lowest level) with 2048 tokens, and an answer that isn't a number no longer rests it. DeepSeek V4 Flash, GLM-5.3 Flash and MiMo v2.6 Flash now get 20/20. The site's routing demo opens on By intent: a turn is classified once, goes to its rule's model, and its tool rounds stay there
2026-09-26 12:34:55 +08:00
yetone
d9ff79ae44
docs: Intent routing, in English and Chinese — when the classifier is asked and when not, the exact prompt and what of the message it sees, how its answer is read, what happens when it fails or is slow, the rest of the turn (held, failover, outgrown, waits, subagents), reading the trace, latency/cost/privacy, writing intents, the numbers, and a FAQ; with screenshots of the rules and the trace
2026-09-26 11:30:09 +08:00
yetone
bc720c8d87
group: a rule can be for a kind of message — intent="writing or fixing tests": as a user's turn begins, the group's classifier (any model magpie has, best a small fast one) is asked once which of the intents that may match the message is, and the turn stays with the answer through its tool rounds; it isn't asked when no intent rule could decide, the same message isn't asked about twice, and when it fails or is slow (8s) no intent matches and it rests 30s. The trace says what it was asked and said; Routing's rule editor has "asks for" and the classifier picker, and magpie group rule add … intent=… classifier=… / magpie group rule classifier from the terminal. A sub-millisecond reply no longer shows as NaN s in the trace
2026-09-26 11:09:13 +08:00
yetone
696c8e70e7
group: rules send a kind of turn to a chosen model — a group's Rules (Routing view, or magpie group rule add|rm|mv) put one of its models first for a turn that is long (tokens ≥ N), carries an image, asks for reasoning (on or at least a level) or comes from certain agents; the first that matches decides as the turn begins and the turn stays there through its tool rounds, moving only if it outgrows its model's context, the others staying behind it for failover; a subagent keeps a place of its own so a rule can send it elsewhere while its agent stays; the trace says which rule sent a turn where. Turn affinity also now sees past the system message Claude Code puts after tool results, which made each of its tool rounds look like a new turn
2026-09-26 03:53:33 +08:00
yetone
31fbf611e7
docs: what an import link's catalog gives — besides names, context sizes and reasoning levels it is the model list when the provider's /models can't be read and the prices behind the Usage page's USD estimate, and several ids may be given
2026-09-26 02:47:19 +08:00
yetone
c0cbf90eeb
agent(zcode): ZCode is an agent — its provider field puts every magpie model in ZCode's own model picker, as a provider named magpie in ~/.zcode/v2/config.json (kind anthropic, asked at the gateway's /v1/messages), kept in step with the catalog like OpenCode's list, and taken out again when cleared; its requests are known by the ZCode/ User-Agent ( #72 )
2026-09-25 23:53:59 +08:00
yetone
032bcfc8b0
provider: the Grok subscription is called Grok (SuperGrok) — the plan xAI sells, so it reads as the account it signs into; Grok Build stays the name of the agent, the grok CLI the subscription runs through
2026-09-25 18:33:21 +08:00
yetone
f7112a9e9d
agents: Grok Build — xAI's grok CLI — is an agent: its model is set in ~/.grok/config.toml ($GROK_HOME), and a model through magpie adds the catalog there as [model."magpie/…"] tables pointed at the gateway with magpie's own key, so a request never carries the user's xAI sign-in and the catalog joins Grok's own models in /model; its effort is [models] default_reasoning_effort, its requests are known by grok-shell; the Grok subscription is called Grok Build too
2026-09-25 18:26:50 +08:00
yetone
bea2cec91f
site: the Routing shot shows four agents — Claude Code, Codex, OpenCode, Crush — sending at once through three routing groups, with Kimi rate-limited and sitting out; in every shot the magpie icon lines up with what's under it, where it had kept the room the Mac window leaves for traffic lights a screenshot doesn't have; and the homepage's Providers shot ends where its list does
2026-09-25 17:21:21 +08:00
yetone
7d0069ab93
site: the import docs come in Chinese too (/docs/zh/import, with its own screenshot of the dialog and the link builder's messages in Chinese), and each page links to its other language; the start docs show what each step looks like — the Add provider sheet, the Agents window, routing groups and Usage — in light and dark, English and Chinese
2026-09-25 16:41:48 +08:00
yetone
637b2458ee
provider + gateway: Google sign-ins — Gemini CLI's and Antigravity's — are subscriptions of magpie's, so any agent can use their models ( #4 ); Gemini CLI's own login in ~/.gemini is read as it is, or an account is signed in from magpie with Google's OAuth, its token refreshed in memory, and each request goes to Code Assist wrapped as the app wraps it, with the project Code Assist set the account up with; Google now serves Gemini CLI's sign-in only to Code Assist Standard and Enterprise, which need a Cloud project, named with magpie accounts project or GOOGLE_CLOUD_PROJECT in ~/.gemini/.env and said so where the account is shown; Google may suspend an Antigravity account used outside Antigravity, so magpie says that and asks before adding one
2026-09-25 15:53:33 +08:00
yetone
2779d03caa
provider: Ollama Cloud is a preset of its own, with Ollama's icon and where to get a key (ollama.com/settings/keys) — its hosted models answer the local server's API at ollama.com with a key: chat at https://ollama.com/v1 , Anthropic's messages at https://ollama.com , and the model list from /v1/models, and models.dev's ollama-cloud names them; the import links take it too
2026-09-25 15:02:31 +08:00
yetone
ea09310872
site: the getting-started guide says outright that a model two providers serve becomes a group by itself — group/auto-<model>, over every provider serving it, the name matched however each vendor spells it, hidden with magpie group rm — which it said in passing, and someone trying magpie found it out by testing and asked for it to be written down
2026-09-25 14:48:28 +08:00
yetone
6882ceac7d
site: a getting-started guide, in English at /docs/start and in Chinese at /docs/zh/start (/docs and /docs/zh open it) — someone who runs Claude Code, Codex and Paseo every day found magpie confusing at first and the site had only the Add to magpie page for vendors; the guide says what magpie is for and how the setup goes: add the providers you have (subscriptions signed in to in magpie, a vendor's preset and its key, any compatible URL, or Import… from Claude Code and Codex), pick a model for each agent and what that writes into its config, a new session to pick it up, then routing groups when there are several accounts (the Routing view and magpie group), Usage, profiles, the commands and a short FAQ, the Chinese one in the app's own Chinese labels. The home page's Docs link and every docs page's nav and footer lead to it, and on a phone the docs nav keeps the brand, the language, the theme and Download
2026-09-25 14:18:13 +08:00
yetone
b3705cbb5a
cli: routing groups are made, changed and removed from the terminal too ( #55 ), where only the Routing view could — magpie groups lists them, yours then those magpie found (a removed one named with how to bring it back, a member no provider serves now marked so, the agents set to each); magpie group add <name> models=<m1>,<m2> routing=smart|order|rotate|usage stays=auto|session|turn|off makes one, its id taken from the name and numbered past one taken as the Routing view does; magpie group set <id> k=v… changes name, routing, stays and the models — models= the whole list in order, models+= and models-= one at a time — and changing one magpie found makes it yours; magpie group rm hides one magpie found, for magpie group restore to bring back; magpie group <id> shows one. Each saves through the same code the Routing view's does, so the file holds the same group and agents' model lists follow the change. A model is its provider/model id as magpie models lists it, or a bare model id one provider serves; one no provider serves, or several do, says which it could mean, and a routing or stays value magpie has none of says the ones it has, where the saved group would have quietly gone back to the default
2026-09-25 14:06:15 +08:00
yetone
b72985a9cc
agent: add Hermes Agent ( #49 ) — magpie adds itself to ~/.hermes/config.yaml ($HERMES_HOME) as the provider "magpie" under providers (the gateway as chat completions, the catalog as its models) and points model.provider at it, with the model in model.default; the provider and model the user had are stashed and put back when they pick one of Hermes's own or go back to the default. Hermes sends its own User-Agent only from a recent release on, so the entry sets it for the gateway's usage view
2026-09-25 09:08:08 +08:00
hanhotfox
cd0eccfa58
agent: add Devin ( #43 )
...
* agent: add Devin — model via agent.model in config.json, subscription via devin acp over ACP
* gateway: surface devin acp read errors to waiters
* providers: fix devin sign-in exchange; account editor and picker fixes
* gateway: scope the devin deny rules and copy credentials when a link can't be made
* gateway: note devin never rewrites credentials.toml during a session
2026-09-25 07:16:21 +08:00
yetone
d8ee8d1af3
community: magpie has a Discord — the site links it from the header, the footer and a card above the download, Settings has a Community row that opens it, and the README a badge and a Community section
2026-09-25 01:22:16 +08:00
yetone
41931e2895
agent: omp (oh-my-pi) — its model picked in magpie like any agent's; a model through magpie adds magpie as a keyless provider in ~/.omp/agent/models.yml with the catalog as its models, and sets config.yml's modelRoles.default to magpie/<provider>/<model>; its other roles and the rest of both files stay as they are, comments too, and default takes magpie's entry out unless another role still uses it ( #34 )
2026-09-24 22:36:15 +08:00
yetone
be1b3967f4
agent: Command Code — its model picked in magpie like any agent's; a model through magpie adds magpie as a keyless provider in ~/.commandcode/providers.json with the catalog as its models, and sets settings.json's model to magpie/<provider>/<model>; its own models stay as they are, and default takes magpie's entry out; Command Code still wants its own sign-in ( #32 )
2026-09-24 21:44:09 +08:00
yetone
34a03fb0d8
site: the smart routing demo runs on a clock — each request an hour, every account counting down to its reset; Claude Max, resetting soonest, goes first and renews with little left unused, then resets last, and Claude Pro, next to reset, takes over; the point on it is now reset-aware
2026-09-24 21:35:59 +08:00
yetone
ad1395f3bc
routing: smart routing goes by when each account's allowance resets — of the accounts with quota to spare, the one renewing soonest goes first, since what it has left is lost at the reset while one renewing later keeps; one whose reset isn't known comes after, a few minutes apart counts as the same hour so the prompt cache stays warm, and running low still keeps an account for last; the site's routing demo shows each account's reset
2026-09-24 21:29:34 +08:00
yetone
e2051a4268
site: the routing demo adds a second Claude subscription — a Claude Max and a Claude Pro side by side, the Pro rate limited and passed over for the next, beside ChatGPT, OpenRouter and Copilot
2026-09-24 21:01:22 +08:00
yetone
13a1604070
site: the smart routing demo shows real vendors — a Claude Max, a ChatGPT Pro, an OpenRouter key and a Copilot Business seat, each with its vendor's icon, and the captions name them by vendor
2026-09-24 20:50:15 +08:00
yetone
96e44c67d5
agents: DeepSeek Harness (dsh) — its model picked in magpie like any other agent's: dsh's own V4 Pro and Flash, or any model magpie serves, which puts the gateway in ~/.dsh/config.yaml with the whole catalog in dsh's /model; the TUI, dsh -p and dsh web all start on it, the user's own entries stay, one magpie replaced comes back when it's set back to default, and a DeepSeek endpoint set in dsh's settings, which dsh puts over it, is pointed out ( #27 )
2026-09-24 20:22:22 +08:00
yetone
bf78700655
site: smart routing shown working — requests travel from Claude Code through magpie to the account the strategy picks, a tab for each (smart, in order, in turn, least used first); an account running low is kept for last, one answering 429, 402 or 503 sends the request back to magpie for the next, rests as long as it should and comes back, captions say what happened, and the count of errors that reached the agent stays at 0
2026-09-24 20:11:28 +08:00
yetone
2cba789189
site: the Providers screenshot's logo lines up with the icons under it — the gap the window's traffic lights leave is gone from the crop
2026-09-24 19:56:36 +08:00
yetone
bba15a4ee6
site: smart routing on the home page — a section of its own, linked from the nav: several accounts and keys on at once, the first kept while it has quota to spare, one out of credit, out of quota or rate limited passed over until it can answer, a failing one stepping back while the next answers; beside it a card of four Claude accounts, one serving and the others resting, each saying why
2026-09-24 19:47:20 +08:00
yetone
eaf0b55de1
site: the worker adds the Web Analytics beacon to each page itself — Cloudflare's automatic injection skips responses a worker returns, and since the www redirect every page is one
2026-09-24 17:34:37 +08:00
yetone