yetone 95c572e91e gateway: a Claude subscription conversation's next turn goes to the Claude Code that had its last, told only what the user said since, so the conversation Claude Code keeps goes on as it began and its cached prompt is read again — each turn started a new run from the whole history in one message, which shared nothing with the cache but Claude Code's own prompt, so every turn wrote some 5.7K tokens to the cache again where it now writes about 100 (a three-turn conversation went from 37% of its input cached to 79%, one with tool calls from 63% to 87%, about 99% past the first call); a run waits for its conversation up to 20 minutes, six at most, and is found again by what the conversation has been so far, else a new one starts as before; and it is set waiting before the reply's last event, which a quick agent answers at once. Anthropic's usage leaves out what the prompt wrote to the cache, and the OpenAI and Gemini counts magpie gave from it did too, so Codex was told a Claude turn of 26K tokens took 2; and an agent that hangs up once the last event is in (Codex does, before the ChatGPT backend closes its end) had its call logged as canceled, 499, though it was answered in full

2026-09-25 11:44:17 +08:00

..

agent

codex: subagents can be put on a magpie model of their own — Codex's spawn_agent tool lists only the first five models it knows, its own ahead of magpie's, so signed in a model spawning a subagent never saw a magpie model to pick; Codex gets a subagents field that writes [agents] default_subagent_model, the model a subagent starts on when none is asked for, offered once Codex runs through magpie and taken out again when it steps back to its own models

2026-09-25 09:23:33 +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

codex: a magpie model that takes images says so in the catalog magpie gives Codex, which otherwise drops an attached image before sending — every magpie model was listed as text-only, so a picture pasted into Codex never reached a vision model; whether a model takes images is what its vendor's models.dev entry says, or for one served by a vendor models.dev doesn't list, what most of the providers serving that model say, and a routing group takes them only when every member does

2026-09-25 06:59:45 +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: a magpie model that takes images says so in the catalog magpie gives Codex, which otherwise drops an attached image before sending — every magpie model was listed as text-only, so a picture pasted into Codex never reached a vision model; whether a model takes images is what its vendor's models.dev entry says, or for one served by a vendor models.dev doesn't list, what most of the providers serving that model say, and a routing group takes them only when every member does

2026-09-25 06:59:45 +08:00

edit

codex: subagents can be put on a magpie model of their own — Codex's spawn_agent tool lists only the first five models it knows, its own ahead of magpie's, so signed in a model spawning a subagent never saw a magpie model to pick; Codex gets a subagents field that writes [agents] default_subagent_model, the model a subagent starts on when none is asked for, offered once Codex runs through magpie and taken out again when it steps back to its own models

2026-09-25 09:23:33 +08:00

gateway

gateway: a Claude subscription conversation's next turn goes to the Claude Code that had its last, told only what the user said since, so the conversation Claude Code keeps goes on as it began and its cached prompt is read again — each turn started a new run from the whole history in one message, which shared nothing with the cache but Claude Code's own prompt, so every turn wrote some 5.7K tokens to the cache again where it now writes about 100 (a three-turn conversation went from 37% of its input cached to 79%, one with tool calls from 63% to 87%, about 99% past the first call); a run waits for its conversation up to 20 minutes, six at most, and is found again by what the conversation has been so far, else a new one starts as before; and it is set waiting before the reply's last event, which a quick agent answers at once. Anthropic's usage leaves out what the prompt wrote to the cache, and the OpenAI and Gemini counts magpie gave from it did too, so Codex was told a Claude turn of 26K tokens took 2; and an agent that hangs up once the last event is in (Codex does, before the ChatGPT backend closes its end) had its call logged as canceled, 499, though it was answered in full

2026-09-25 11:44:17 +08:00

gui

gui: copying goes through magpie to the system clipboard — the app's window loads its page from a scheme where the page's own clipboard API is refused, so every copy button only put the text in the status line; the page asks magpie first and falls back to that API in a browser tab

2026-09-25 09:44:45 +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

codex: a ChatGPT account's requests are made as Codex CLI makes them, as Alma's Codex plugin does — the backend gates its newest models on a Codex User-Agent (gpt-5.6-luna answered 404 "Model not found" to magpie's), so a request now says it comes from codex_cli_rs, carries the instructions the account's model list gives each model (kept on disk beside the list, for the gateway to find though another process asked, else Codex CLI's copy, else Codex's generic prompt) with the client's own riding first in the input, and is shaped the way Codex sends one: no stored references or item ids, a tool output without its call told as a note, reasoning summaries and encrypted content asked for, tool_choice auto; and a conversation whose client names none gets a prompt_cache_key of its own, the same on every turn, taken from how the conversation starts, so its cached prompt is found again (Claude Code through magpie went from 74% of its input cached to 96%, where requests without one landed on caches that didn't have it)

2026-09-25 11:44:17 +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

agent + usage: each agent says what its User-Agent begins with, beside its name and icon, and the gateway tells requests apart by that — usage kept a list of its own, which had to be kept in step with the agents by hand and wasn't (DeepSeek Harness, omp and Command Code were missing from it, so they were drawn with no logo); a new agent is now known by its requests as soon as it is described

2026-09-25 05:51:32 +08:00