yetone eb4cc3437d gateway: a request an upstream fails is failed over rather than handed back — a model the provider says it doesn't serve (Copilot's "not accessible via the /chat/completions endpoint", "model does not exist" and the like) goes on to the next one, as a 401, 404, 429 or 5xx already did; an error a stream begins with, before any of its content (Anthropic's overloaded error after message_start, a Chat error chunk, Responses' response.failed), is held and failed over as an error status is, while one after content has begun reaches the agent as it came; the last one left, or the only one, is tried again twice after a failure that may pass (408, 5xx, 529, a 429 that says when), a second and then two apart or as Retry-After says; and an agent that goes away mid-request is counted as canceled, resting nobody and asking nobody else. One that answers stops resting. The Routing view tells each of these

2026-09-25 05:24:44 +08:00

..

agent

gateway(routing groups) + gui(picker, gateway, routing) + codex: routing groups come first in the model picker under a routing icon of their own, each shown as its providers' icons stacked, and are listed first in the Gateway view's models too; a model is found to be the same under the ids its vendors give it — claude-opus-5-5 and claude-opus-5.5, dated or not — so the Claude subscription's Opus 5.5 joins its group; keys made for different protocols are pools apart, a request going round the keys that suit it before trying another's; Codex's model list is asked for as the newest Codex on the machine (codex --version) rather than the version its cache last wrote, so models only newer clients are shown — GPT-6 Sol and Luna — are listed; the Routing view keeps its providers in one order rather than reshuffling them per request; mask icons in the picker have a size to fall back on, so OpenRouter's and Copilot's show

2026-09-25 05:01:18 +08:00

backup

backup: everything set up in magpie carried to another machine in one file — magpie backup writes the providers with their keys (or none, with --no-keys), the pictures picked for them, the settings, the profiles and every agent's model, sealed with a passphrase (AES-256-GCM, PBKDF2-SHA256) so nothing in it reads without it; magpie restore puts it in, replacing providers by id, keeping the keys already there for one that came without, and setting models only for the agents installed there; subscriptions stay with the machine they were signed in on (#28)

2026-09-24 20:34:15 +08:00

catalog

provider(copilot) + gateway: each request goes straight to an API its model is served on, as the provider's model list says, rather than being learned from a refusal — Copilot's list gives every model its endpoints (GPT-6 and 5.5 on /responses alone, Claude on /v1/messages and /chat/completions, Gemini and Kimi on /chat/completions), they are kept with the cached list, and the gateway picks among them, relaying the agent's own API when it is one and translating otherwise; a refusal is still caught for a provider that doesn't say. Copilot's Anthropic endpoint is used too, so Claude Code reaches Copilot's Claude models without translation; a turn that only returns tool results is counted as the agent's (X-Initiator) in Anthropic's format as in the others, and images in Anthropic and Responses requests are flagged as Copilot asks. The provider test asks each endpoint with a model served there

2026-09-25 05:22:52 +08:00

claudebridge

gateway: a Grok subscription (SuperGrok, X Premium+) works like a Cursor one — magpie runs the signed-in Grok Build CLI in a home of its own (none of the user's hooks, skills, rules or MCP servers; only search_tool/use_tool, reaching magpie's MCP tools), borrowing the user's token through magpie grok-token without touching their sign-in; the add sheet has a Grok tile that signs in with grok login's device code

2026-09-24 17:35:36 +08:00

codexcat

codex: magpie's models join Codex's own rather than replacing them — signed in (ChatGPT or an API key), Codex keeps its built-in OpenAI provider and sign-in and is pointed at magpie with openai_base_url alone, so its official models still go to OpenAI on the user's own account, its threads (listed per provider) stay together, and the Codex app keeps its model picker; magpie's gateway answers at /backend-api/codex, passing Codex's own models through as they came, serving magpie's (provider/model) itself, and handing out OpenAI's model list with magpie's after it for /model. Compacting a magpie model's conversation is done by that model with Codex's own prompt; Codex's compressed request bodies are read, and usage is counted for both. Not signed in, magpie stays a provider of Codex's as before; a magpie set up that way moves over the next time a magpie model is picked

2026-09-25 02:42:24 +08:00

edit

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

gateway

gateway: a request an upstream fails is failed over rather than handed back — a model the provider says it doesn't serve (Copilot's "not accessible via the /chat/completions endpoint", "model does not exist" and the like) goes on to the next one, as a 401, 404, 429 or 5xx already did; an error a stream begins with, before any of its content (Anthropic's overloaded error after message_start, a Chat error chunk, Responses' response.failed), is held and failed over as an error status is, while one after content has begun reaches the agent as it came; the last one left, or the only one, is tried again twice after a failure that may pass (408, 5xx, 529, a 429 that says when), a second and then two apart or as Retry-After says; and an agent that goes away mid-request is counted as canceled, resting nobody and asking nobody else. One that answers stops resting. The Routing view tells each of these

2026-09-25 05:24:44 +08:00

gui

gateway: a request an upstream fails is failed over rather than handed back — a model the provider says it doesn't serve (Copilot's "not accessible via the /chat/completions endpoint", "model does not exist" and the like) goes on to the next one, as a 401, 404, 429 or 5xx already did; an error a stream begins with, before any of its content (Anthropic's overloaded error after message_start, a Chat error chunk, Responses' response.failed), is held and failed over as an error status is, while one after content has begun reaches the agent as it came; the last one left, or the only one, is tried again twice after a failure that may pass (408, 5xx, 529, a 429 that says when), a second and then two apart or as Retry-After says; and an agent that goes away mid-request is counted as canceled, resting nobody and asking nobody else. One that answers stops resting. The Routing view tells each of these

2026-09-25 05:24:44 +08:00

netproxy

net: requests go through a proxy — Settings → Proxy, or the environment's, or the system's (#8)

2026-09-24 12:48:01 +08:00

profile

agent: Claude Code's opus, sonnet, haiku and fable tiers can each take their own model (#3)

2026-09-24 12:38:41 +08:00

provider

provider(copilot) + gateway: each request goes straight to an API its model is served on, as the provider's model list says, rather than being learned from a refusal — Copilot's list gives every model its endpoints (GPT-6 and 5.5 on /responses alone, Claude on /v1/messages and /chat/completions, Gemini and Kimi on /chat/completions), they are kept with the cached list, and the gateway picks among them, relaying the agent's own API when it is one and translating otherwise; a refusal is still caught for a provider that doesn't say. Copilot's Anthropic endpoint is used too, so Claude Code reaches Copilot's Claude models without translation; a turn that only returns tool results is counted as the agent's (X-Initiator) in Anthropic's format as in the others, and images in Anthropic and Responses requests are flagged as Copilot asks. The provider test asks each endpoint with a model served there

2026-09-25 05:22:52 +08:00

settings

net: requests go through a proxy — Settings → Proxy, or the environment's, or the system's (#8)

2026-09-24 12:48:01 +08:00

tui

agent: Claude Code's opus, sonnet, haiku and fable tiers can each take their own model (#3)

2026-09-24 12:38:41 +08:00

update

update: Update updates magpie in place — a click downloads the new version and restarts into it, asking for the password when magpie can't replace itself, instead of opening the release page; only a magpie running from its disk image or a temporary copy is sent to the download page, with why

2026-09-25 01:35:24 +08:00

usage

provider: a custom provider can name several catalogs (catalog=openai, deepseek) — a gateway reselling many vendors gets names and reasoning levels for all of them, prefixed ids like deepseek/deepseek-chat included (#17)

2026-09-24 14:10:53 +08:00