Every agent's model. One place. Codex on DeepSeek, Claude Code on Kimi, from the menu bar.
gateway: another magpie added by hand rests only the model it refused
yetone4e5b2ad81cd5
diff --git a/docs/subsystems/gateway-routing.md b/docs/subsystems/gateway-routing.mdindex 50828cd61..4e28b674b 100644--- a/docs/subsystems/gateway-routing.md+++ b/docs/subsystems/gateway-routing.md@@ -119,7 +119,7 @@ recorded as a prediction failure (`noPrediction`).- A pause rule (`Rule.Pause`, `pause=<model>`; John on Discord: a model of the group paused in its vendor's peak hours) leaves the model it names out of the group while it holds (`provider.PausedOut`, on `ruleClock`): the group's own rules and each nested group's on the way down to a member, a group named taking all its models, and a model named taking it wherever a group in the group has it (#625). It runs before planning, on every request rather than once a turn, so the model is not first, not a failover, and not kept by affinity, and comes back as soon as the hours end. It holds by hours, days, agents and folders only (`cleanRules` refuses another condition), and is not a send-to rule: `Matches`, `MatchRule`, `ThenUses`, `Ruled` and the compaction rules leave it out. A send-to rule naming a paused model finds it unready and the group routes as without it. The trace keeps what was paused (`GroupRef.Paused`), and the Routing page says so. Every model paused answers 503 (`pausedError`) naming each rule. Embeddings go by the same pauses; manual groups have no rules (`Live`), so none pause there. A pause by folder (#1606, Ti800: a subscription's quota kept for the long task in one folder, `pause=<model> except-folders=~/big-task`) reads the folder only when such a pause is on the way (`provider.PausesByFolder`, then `workDir`): outside its except-folders, which includes a request that says no folder (a subagent's or a small model's that doesn't), the model is left out; with `folders=`, only requests known to be in them. Embeddings and System One's decision calls have no folder. `Paused.Folder`/`ByFolder` carry what was read, and the Routing page says the folder or that none was said. `rules_pause_test.go`, `TestPauseByFolder`, `TestPauseByFolderRule`, `TestParsePauseByFolder`, `routing-pause-folder.test.cjs`.- A rule's hours and days (`Rule.Time`, `provider.TimeWindow`) are read on `ruleClock` in the zone they were set in (`TimeWindow.Zone`, an IANA name; gaubeebangeel on X: magpie on a cloud server in UTC, its user in Beijing, the hours 8 off). The GUI saves the browser's zone when the hours or days are changed in the editor and leaves a rule's zone alone otherwise; the CLI (`magpie group rule add … time=09:00-18:00@Asia/Shanghai` or `tz=`) and the TUI save the one typed, or this computer's (`provider.LocalZone`: `$TZ`, `time.Local`, the `/etc/localtime` link) when it has an IANA name. A window with no zone, every one saved before zones were kept, stays on magpie's own clock. A zone magpie doesn't know is refused on save (`TimeWindow.clean`), and one in a file edited by hand makes the window never hold (`zoneOf`): the rule is as if absent, never always on and never hours off. Zones come from Go's embedded tzdata, so Windows knows them too. `/api/groups` gives magpie's clock (`clock`: its zone and offset in seconds), and when it differs from the hours' zone the Routing page tells the zone beside them, on the group's rules and in the editor (`zoneNote` in [`plugins/routing/client.js`](../../internal/gui/assets/plugins/routing/client.js)): the zone's name, or the server's offset for hours with none. `TestRuleTimeWindowInItsZone`, `TestRuleTimeWindowInItsZoneAtTurnStart`, `TestRuleTimeWindowUnknownZone`, `TestParseRuleTimeZone`, `TestGroupRuleTimeZoneCmd`, `routing-time-zone.test.cjs`.3. Candidates come from `planGroup` for a group or `plan` for a provider. They are filtered by `sealedReaders` and `allowedCandidates`. An account past its share is held out of the candidates (`capHeld`): a usage cap's share, each window at its own where the account gives it one (`AccountWindowCaps`, willz on Discord: 50% of the five hours, 40% of the week) and at the account's cap otherwise, or 100% of a window for a Codex account set not to spend its credits (`provider.HoldCaps`, `WindowCaps.Of`, `CodexNoCredits`). A ChatGPT account's call on `codex-auto-review`, which OpenAI counts in no window, is held by no usage cap, only by credits it may not spend (`freeOnChatGPT`, #1593, `TestAccountCapLetsAutoReviewThrough`). The account is held while any window is past its own share, and `cappedError` and the trace name the fullest such window's share and cap. When every candidate is held and one held for its credits spends its resets by itself, `autoReset` spends a reset on it and it is tried (`planned.held`); otherwise a capped or barred set returns `cappedError` or `barredError`. Then `affine` moves the conversation's last answerer first, unless it is resting or nearly used up. An `X-Magpie-Account` header (`AccountHeader`) pins the request to one account: only that account is tried, and when it can't answer the caller is told why.-4. The candidate loop calls `attempt` on each candidate in turn, through a `holdWriter`. The writer holds the reply until it is clearly passing. A candidate that fails before anything is sent rests (`failure`): out of credit for 30 minutes, out of quota until reset, rate limited until retry-after, otherwise a minute and longer on repeats: doubled each time, up to `longestRetry` (10 minutes) for a failure and `longestRateRest` (30 minutes) for a rate limit back as soon as its rest is over, or up to the provider's own `restCap` in minutes (`Provider.RestCapOr`, at most `MaxQuotaRest`; `magpie provider rest-cap <id> 4h`, #2008: a free key down for hours was asked every 10 minutes). A time the vendor names stands over it as before (`TestOwnRestCap`). The failure count is kept per key or account (`restKey`), and any of its models' answers clears it (`served`). Each model's own count (`restID`) is kept beside it and cleared only by that model's answer (`servedCandidate`): once it is past the account's, a sibling model answered since it last did, so the failure is the model's and it climbs its own ladder and rests alone, its siblings still served (#2241, weizsw: an Antigravity seat's gemini-3.5-flash-lite rested a minute 41 times of 43 while gemini-3.8-flash kept answering; `TestModelLadderClimbsPastSiblingAnswers`). Every model failing with no answer between still climbs the account's ladder and rests the account, and a candidate naming no model has the account's count alone. `rest-cap <id> off` (`provider.RestCapOff`, `restCap: -1`) is for a relay or account pool whose unknown errors come now and then and pass by the next request (Kismet Alan on Discord): a failure that says nothing of why (`failOther`: a 5xx, a dropped connection) then rests nobody and isn't counted, its trace rest `by: "off"` with no time left. A 401 or 403, a model not served, an account's window full, a rate limit (magpie's own 30-minute cap), quota, credit and a restriction still rest it as before (`TestRestCapOff`). A provider the user added can be set never to rest for a limit instead (`provider.LimitRestOff`, `limitRestOff` in providers.json; the editor's Advanced fold, "Set it aside when out of quota or rate limited", ticked by default): a refusal `restAfterMarked` reads as out of quota, out of credit or rate limited, and any 429, then rests nothing, isn't counted or sunk, and is `by: "off"`; `restDrawer` rests no image model of it. The next request is sent to it as usual. It is for a relay whose limits pass in a moment (zoecats on Discord: a local aggregator said "quota exhausted" while it switched upstreams, and magpie answered itself for 30 minutes; `TestLimitRestOffKeepsAsking`, `TestLimitRestOffRestsNothingForALimit`). A 401, a model not served and a plain failure still rest it. The shortest cap otherwise is a minute, the first rest; `rest-cap <id> 30s` is turned away and names `off`. A 400, 403, 404 or 422 that says the model isn't served (`unservedWords`) and says nothing of quota, credit or a rate limit rests only that key's or account's model (`modelRefused`, keyed by `restID`, its backoff counted apart): its other models are still served first in order (#1235, SenseNova's 403 "model is not available in the current token plan"). A Google account's Code Assist (the Antigravity and Gemini CLI built-ins) answering 404 `NOT_FOUND` ("Requested entity was not found.") rests its model the same way, as its endpoint is the same for every model (`codeAssistModelMissing`; Packing1 on Discord: Argon, listed for a Google AI Pro account, answered 404 and rested the whole account; `TestCodeAssistMissingModelRestsTheModel`). A refusal for want of quota, credit or rate, for an account its vendor restricted, or for a verify it asks of its account there, from another computer's magpie (a Remote magpie provider, LAN share) rests only the model it was about (`remoteModelRest`, keyed by `restID`, in `restAfterMarked` and `rateRest`): that magpie serves each of its models from its own providers and rests them itself, so one out of quota there says nothing of the others (bigsteven on Discord: a 429 for one model rested every model on the remote for the 3 hours it named, so a group never moved on to the remote's other models; `TestRemoteMagpieQuotaRestsTheModel`, `TestRemoteMagpieRestrictedRestsTheModel`). Its key refused, the computer unreachable, or the key's own limit there (`keyLimited`'s 429, which carries `X-Magpie-Limit-Reset`, `remoteKeyLimitHeader`), still rests it whole: #2077's reporter had a Claude Code session limit on the other magpie refuse its Qoder models here (`TestRemoteMagpieRestsTheModel`, two gateways over HTTP; `TestRemoteMagpieKeyLimitRestsTheKey`). A 400, 404, 410 or 422 that says the model is retired (`retiredWords`: OpenCode Zen's 410 `ModelDeprecated` "Model exo-free has been deprecated.", whose own model list still names it; MOMO on Discord) rests only that model the same way, is retryable so a group's next member or another provider of it is asked, and is remembered (`provider.Retire`, `retired.json` beside `providers.json`): the model leaves that provider's entries in the catalog (`buildEntries`), so /v1/models, every agent's model list and the found groups go without it, until a request on it is answered again (`Unretire` in `servedCandidate`) or a week has passed. A refresh of the vendor's list doesn't bring it back early, since that list is where it still is. A `provider/model` request for it is still sent. A 400 or 422 that says this upstream's API can't take the request's shape (`shapeWords`: xAI's 422 "unknown item type" (#350), OpenAI's "Unknown parameter", and a limit of a model's own on tool schemas, OpenCode Go's 400 "JSON schema exceeds the maximum nesting depth of 10 levels" on muse-spark-1.3-contributor, #1870), or that it is served on another API than the one asked (`wrongEndpoint`, once the member has tried every API it has a URL for: #2670, a relay with a Chat URL alone refusing tools with reasoning and `none` too), rests nobody: the next candidate is asked once (`shapeRefused`, `failShape`), and the last one's error reaches the agent. A request missing what every API requires ("field required") isn't one, nor is a 200 that mentions it. Command Code's Provider API turning a request away with nothing but a trace id (`unsaidWords`: `{"message":"invalid request error trace_id: <hex>","type":"invalid_request_error"}`, a 400, or a 422 before) is handled the same way: it turns away a request whose history and asked-for output together are over a limit below the model's listed context (the reporter's A/B: one ~748K-token agent conversation answered 200 with `max_completion_tokens` 64000 and this 400 with 384000, the model's listed max output), which another member's model may take, and the key is fine (#2313, `TestGroupFailsOverCommandCodesBare400`). Its overflow, which names the model's context length before the trace id, and an error that names a `param`, aren't one. A relay's own cap on one request's input that says so (`tooLongRe`: B.ai's 400 "Input token exceed the limit", on a 380K request under the model's 1M window; #2445, worksyang) is taken as an overflow (`overflowed`), which no word list of `retryable` matched: a group's next member that may hold the request is asked (`withRoom`, `failOverflow`), nobody rests, another account of the same model isn't asked, and with no member left the agent is told the conversation is too long, so it compacts. A rate limit worded with input tokens (`paceWords`) isn't one, and a plain bad request is still asked of nobody else (`TestRelayInputCapGoesToTheNextMember`). A subscription account that fails any other way with a window full, by magpie's latest reading of its windows, rests until that window renews. A 401 or 403 is the exception: one that names a quota is out of quota already (`usedUpWords`), and one that doesn't is about the key or the request, so it rests on the backoff ladder whatever the reading says (plugins#243, zygs1083-dotcom: a Factory account read at 98% sat out its week over one plain 403; `TestPlain403DoesNotRestUntilTheWindow`). A plain 403 (`plainForbidden`: no quota, credit, rate, verification, restriction or model not served) from a second key or account of the same provider, model and reasoning in one request is the request refused, not each account: neither rests, the first one's rest and counted failure are taken back (`forbiddenAlike`, `unforbid`), and the provider's other mates are asked last (`matesLast`). Before, that one request walked every account of the provider into backoff (`TestPlain403OnTwoMatesRestsNeither`). One account's plain 403 alone still rests it. Both quota rests and window rests are held to `longestQuota` (8 days), so a reset time read wrong (a year off) doesn't bench the account for that long. The next candidate is then tried. A failed provider waits `fallbackCooldown` (1 minute) at the back. A WorkBuddy account the vendor restricted (#1849: 403 `{"code":11140,"msg":"request illegal","displayMsg":{"en":"Your account has been restricted due to unusual activity",…}}`) rests `restrictedRest` (2 hours) as `restricted` (`failRestricted`), not the minutes of an unknown failure: only WorkBuddy lifting the restriction, after the user's appeal, brings it back. Both shapes are known: the built-in's `wbExplain` and the plugin's `explained()` (0.1.17, the mover's `min`) end the error with `provider.WBRestrictedHint` (`restrictedSaid`), and the vendor's own body, its code 11140 or its words (`provider.WBRestricted`), counts only from a WorkBuddy candidate (`restrictedRefused`, `isWorkBuddy`), as another vendor's 11140 is its own. Bare "request illegal" isn't matched. WorkBuddy's 11128 channel refusal stays `promptRefused` and rests nobody. The Routing page names it "account restricted by the vendor", says the appeal is the way back, and gives the account's row a button that lifts the rest (`/api/gateway/unrest`) once the vendor has. Every other rest a key or account takes (quota, rate limit, retry-after, a failure's backoff) can be lifted by hand the same way (#1869): "Try now" on its row on the Routing page and beside its rest note in the provider's key list. It ends the rest, and with Sink on puts the key back from the back of the order; the backoff count stays, and a refusal after it rests the key again the usual way. Every lift before its time (Try now, `UnrestAll` for a replaced key, `renewed` for windows that renewed) is noted by its rest key (`restingUntil.lifted`) and handed to the Routing page in the trace (`TraceState.Lifted`, `lifted` in `/api/gateway/trace`), and a lift wakes a page waiting on the trace though no route changed (`trace.lifted`). The page stops showing a rest or a sink found before its lift, wherever the lift was asked for (zoecats on Discord: Try now in the provider's editor left Routing at 429 until a restart; `TestTryNowToldToTheRoutingPage`, `routing-lifted-elsewhere.test.cjs`). With another magpie serving the gateway, Try now lifts nothing (#3555). The vendor's safety filter refusing a reply rests nobody, whether it refuses the turn before any of the reply is said or once some of it has been said (`refused`, `refusedAfter`). So does one said in a stream a client is answered whole from (a Codex account is streamed upstream for a `stream:false` Responses, Chat or Messages request): each decoder gives the refusal's error event status 400 and its code (`filterRefused`), a whole reply it cut is answered the refusal rather than its words so far, and Anthropic's error shape, which has no code, carries it in `refusedHeader`; before, it was answered 502 `api_error`, asked again, and each account rested (#3274). `restAfterMarked` itself rests nobody, and counts no failure, for a 400 whose error object `policyRefusal` reads as a refusal, by its code, never by words a body may echo of the request. Its note on the try (and in the error the agent gets when nobody is left) is the vendor's reason, with Anthropic's `stop_details` category and explanation when it gave them (`refusedDetail`, #1768: "safety filter: refusal (category cyber)"); none is made up when it gave none. `stop_details` is carried through the IR (`Event.StopDetails`), so a Claude subscription run through the claude CLI and a translated Anthropic route keep it for an Anthropic client too. How many more candidates a refusal before any of the reply is asked of is Settings' `RefusalRetries` (`refusalAsksAgain`, counted per request in the candidate loop; a group's other members count too): unset, every one left (#248); 0, none (#1925, DD on Discord). When nobody is left, an agent on Anthropic's Messages API gets the held refusal itself, the vendor's 200 with `stop_reason` `refusal` and its `stop_details`, streamed or whole (`holdWriter.handBack`), since that is what Claude Code switches to its fallback model on; a 400 is only an API error to it. Codex and Chat clients still get `failTo`'s 400 (`refusedStatus`), which they don't ask again for. `TestRefusalRetries*` in [`refusal_retries_test.go`](../../internal/gateway/refusal_retries_test.go) cover keys, a group and the Claude subscription. The ChatGPT backend's 502 "response protection is unavailable" is about the request's content, not the account: the same history fails the same on each of its accounts and models. It rests nobody, isn't tried again after a moment, and isn't asked of the provider's other accounts or models; another provider left in a group is asked once (`protectionRefused`, `elsewhere`). One cause is known (#1270): a history that replays the backend's own `web_search_call` in a request that doesn't declare the `web_search` tool is refused so, whatever the account, model or turn (a plain turn, a thread's description, a compaction, Codex's own text compaction for a custom provider with `tools: []`). Every request to the ChatGPT backend with such a history therefore declares cached-only search (`{"type":"web_search","external_web_access":false}`, `provider.DeclareSearch`): an account's in `codexBody`, Codex's own sign-in relayed in `codexUpstreamOn`. It goes in the tools, or for Responses Lite (its header, `reasoning.context` `all_turns`, or an `additional_tools` item already there), which refuses a top-level `web_search`, in the `additional_tools` item. A request that offered no tools gets `tool_choice` `none` so the model can't search; one with a forced choice keeps it. A history without a search, or a request that declares search already, is relayed unchanged; Codex's own `web.run` (a function in the `web` namespace, which Codex offers in place of the hosted tool on a Responses Lite model or with its standalone web search on, and runs through `/alpha/search`) counts as declaring it, since the backend refuses a request carrying both `web.run` and the hosted `web_search` (Savin on Discord, Codex 0.163.0-alpha; `TestSearchedConversationUnderWebRun`). siwc, API-key requests to openai.com and the legacy `/responses/compact` are left as they were. Command Code turning a model away for its Zero Data Retention setting (its plugin's switch, 0.1.14, which sends `x-cmd-zdr: 1`; magpie-community/plugins#246) is a refusal of that request's setting, not of the model or the account: the Provider API's 422 with `"code":"cmd_zdr_no_providers"` and the 400 the plugin makes of Go's error line with `"type":"cmd_zdr_no_providers"` (`zdrCoded`, matched as the error's code or type, never by its words, whose "…a different model.","type":"invalid_request_error" read as a model unserved and rested the model on the account). `keepRetry` notes it beside the error (`zdrHeader`), since the error the agent gets may keep no code (Anthropic's shape, or the 400's numeric code). It rests nobody, anywhere (`restAfterMarked` returns `by: "off"`), so the model answers as soon as the switch is off; it isn't asked of the provider's other accounts at that model, which carry the same header (`notMates`), nor again after a moment; another member, the provider's other models among them, is asked once, and with none left the agent gets Command Code's words (`TestCommandCodeZDRRefusalRestsNothing`, `TestZDRRefusalNeverRests`). Another vendor's refusal in the same words, without the code, still rests the model (`TestZDRRefusalIsCommandCodesCodeOnly`).+4. The candidate loop calls `attempt` on each candidate in turn, through a `holdWriter`. The writer holds the reply until it is clearly passing. A candidate that fails before anything is sent rests (`failure`): out of credit for 30 minutes, out of quota until reset, rate limited until retry-after, otherwise a minute and longer on repeats: doubled each time, up to `longestRetry` (10 minutes) for a failure and `longestRateRest` (30 minutes) for a rate limit back as soon as its rest is over, or up to the provider's own `restCap` in minutes (`Provider.RestCapOr`, at most `MaxQuotaRest`; `magpie provider rest-cap <id> 4h`, #2008: a free key down for hours was asked every 10 minutes). A time the vendor names stands over it as before (`TestOwnRestCap`). The failure count is kept per key or account (`restKey`), and any of its models' answers clears it (`served`). Each model's own count (`restID`) is kept beside it and cleared only by that model's answer (`servedCandidate`): once it is past the account's, a sibling model answered since it last did, so the failure is the model's and it climbs its own ladder and rests alone, its siblings still served (#2241, weizsw: an Antigravity seat's gemini-3.5-flash-lite rested a minute 41 times of 43 while gemini-3.8-flash kept answering; `TestModelLadderClimbsPastSiblingAnswers`). Every model failing with no answer between still climbs the account's ladder and rests the account, and a candidate naming no model has the account's count alone. `rest-cap <id> off` (`provider.RestCapOff`, `restCap: -1`) is for a relay or account pool whose unknown errors come now and then and pass by the next request (Kismet Alan on Discord): a failure that says nothing of why (`failOther`: a 5xx, a dropped connection) then rests nobody and isn't counted, its trace rest `by: "off"` with no time left. A 401 or 403, a model not served, an account's window full, a rate limit (magpie's own 30-minute cap), quota, credit and a restriction still rest it as before (`TestRestCapOff`). A provider the user added can be set never to rest for a limit instead (`provider.LimitRestOff`, `limitRestOff` in providers.json; the editor's Advanced fold, "Set it aside when out of quota or rate limited", ticked by default): a refusal `restAfterMarked` reads as out of quota, out of credit or rate limited, and any 429, then rests nothing, isn't counted or sunk, and is `by: "off"`; `restDrawer` rests no image model of it. The next request is sent to it as usual. It is for a relay whose limits pass in a moment (zoecats on Discord: a local aggregator said "quota exhausted" while it switched upstreams, and magpie answered itself for 30 minutes; `TestLimitRestOffKeepsAsking`, `TestLimitRestOffRestsNothingForALimit`). A 401, a model not served and a plain failure still rest it. The shortest cap otherwise is a minute, the first rest; `rest-cap <id> 30s` is turned away and names `off`. A 400, 403, 404 or 422 that says the model isn't served (`unservedWords`) and says nothing of quota, credit or a rate limit rests only that key's or account's model (`modelRefused`, keyed by `restID`, its backoff counted apart): its other models are still served first in order (#1235, SenseNova's 403 "model is not available in the current token plan"). A Google account's Code Assist (the Antigravity and Gemini CLI built-ins) answering 404 `NOT_FOUND` ("Requested entity was not found.") rests its model the same way, as its endpoint is the same for every model (`codeAssistModelMissing`; Packing1 on Discord: Argon, listed for a Google AI Pro account, answered 404 and rested the whole account; `TestCodeAssistMissingModelRestsTheModel`). A refusal for want of quota, credit or rate, for an account its vendor restricted, or for a verify it asks of its account there, from another computer's magpie (a Remote magpie provider, LAN share) rests only the model it was about (`remoteModelRest`, keyed by `restID`, in `restAfterMarked` and `rateRest`): that magpie serves each of its models from its own providers and rests them itself, so one out of quota there says nothing of the others (bigsteven on Discord: a 429 for one model rested every model on the remote for the 3 hours it named, so a group never moved on to the remote's other models; `TestRemoteMagpieQuotaRestsTheModel`, `TestRemoteMagpieRestrictedRestsTheModel`). Another magpie added by hand, as an OpenAI-compatible provider of the user's own name rather than the preset, is read as one by its reply: a magpie names the provider that answered or held it (`X-Magpie-Provider`, `providerHeader`; `noteMember`, also on a `quotaHeld` or `verifyHeld` answer), as no vendor does, and `keepRetry` notes it as `answeredThereHeader`, since this magpie writes its own provider into the same header of its reply and the note is kept from the client (lagrangepoint1813 on Discord: "Remote Magpie: Claude Code: You've hit your session limit" answered every model of it, from `quotaHeld`, for the five hours it named; `TestAnotherMagpieAddedByHandRestsTheModel`, asked there and held there). Its key refused, the computer unreachable, or the key's own limit there (`keyLimited`'s 429, which carries `X-Magpie-Limit-Reset`, `remoteKeyLimitHeader`), still rests it whole: #2077's reporter had a Claude Code session limit on the other magpie refuse its Qoder models here (`TestRemoteMagpieRestsTheModel`, two gateways over HTTP; `TestRemoteMagpieKeyLimitRestsTheKey`). A 400, 404, 410 or 422 that says the model is retired (`retiredWords`: OpenCode Zen's 410 `ModelDeprecated` "Model exo-free has been deprecated.", whose own model list still names it; MOMO on Discord) rests only that model the same way, is retryable so a group's next member or another provider of it is asked, and is remembered (`provider.Retire`, `retired.json` beside `providers.json`): the model leaves that provider's entries in the catalog (`buildEntries`), so /v1/models, every agent's model list and the found groups go without it, until a request on it is answered again (`Unretire` in `servedCandidate`) or a week has passed. A refresh of the vendor's list doesn't bring it back early, since that list is where it still is. A `provider/model` request for it is still sent. A 400 or 422 that says this upstream's API can't take the request's shape (`shapeWords`: xAI's 422 "unknown item type" (#350), OpenAI's "Unknown parameter", and a limit of a model's own on tool schemas, OpenCode Go's 400 "JSON schema exceeds the maximum nesting depth of 10 levels" on muse-spark-1.3-contributor, #1870), or that it is served on another API than the one asked (`wrongEndpoint`, once the member has tried every API it has a URL for: #2670, a relay with a Chat URL alone refusing tools with reasoning and `none` too), rests nobody: the next candidate is asked once (`shapeRefused`, `failShape`), and the last one's error reaches the agent. A request missing what every API requires ("field required") isn't one, nor is a 200 that mentions it. Command Code's Provider API turning a request away with nothing but a trace id (`unsaidWords`: `{"message":"invalid request error trace_id: <hex>","type":"invalid_request_error"}`, a 400, or a 422 before) is handled the same way: it turns away a request whose history and asked-for output together are over a limit below the model's listed context (the reporter's A/B: one ~748K-token agent conversation answered 200 with `max_completion_tokens` 64000 and this 400 with 384000, the model's listed max output), which another member's model may take, and the key is fine (#2313, `TestGroupFailsOverCommandCodesBare400`). Its overflow, which names the model's context length before the trace id, and an error that names a `param`, aren't one. A relay's own cap on one request's input that says so (`tooLongRe`: B.ai's 400 "Input token exceed the limit", on a 380K request under the model's 1M window; #2445, worksyang) is taken as an overflow (`overflowed`), which no word list of `retryable` matched: a group's next member that may hold the request is asked (`withRoom`, `failOverflow`), nobody rests, another account of the same model isn't asked, and with no member left the agent is told the conversation is too long, so it compacts. A rate limit worded with input tokens (`paceWords`) isn't one, and a plain bad request is still asked of nobody else (`TestRelayInputCapGoesToTheNextMember`). A subscription account that fails any other way with a window full, by magpie's latest reading of its windows, rests until that window renews. A 401 or 403 is the exception: one that names a quota is out of quota already (`usedUpWords`), and one that doesn't is about the key or the request, so it rests on the backoff ladder whatever the reading says (plugins#243, zygs1083-dotcom: a Factory account read at 98% sat out its week over one plain 403; `TestPlain403DoesNotRestUntilTheWindow`). A plain 403 (`plainForbidden`: no quota, credit, rate, verification, restriction or model not served) from a second key or account of the same provider, model and reasoning in one request is the request refused, not each account: neither rests, the first one's rest and counted failure are taken back (`forbiddenAlike`, `unforbid`), and the provider's other mates are asked last (`matesLast`). Before, that one request walked every account of the provider into backoff (`TestPlain403OnTwoMatesRestsNeither`). One account's plain 403 alone still rests it. Both quota rests and window rests are held to `longestQuota` (8 days), so a reset time read wrong (a year off) doesn't bench the account for that long. The next candidate is then tried. A failed provider waits `fallbackCooldown` (1 minute) at the back. A WorkBuddy account the vendor restricted (#1849: 403 `{"code":11140,"msg":"request illegal","displayMsg":{"en":"Your account has been restricted due to unusual activity",…}}`) rests `restrictedRest` (2 hours) as `restricted` (`failRestricted`), not the minutes of an unknown failure: only WorkBuddy lifting the restriction, after the user's appeal, brings it back. Both shapes are known: the built-in's `wbExplain` and the plugin's `explained()` (0.1.17, the mover's `min`) end the error with `provider.WBRestrictedHint` (`restrictedSaid`), and the vendor's own body, its code 11140 or its words (`provider.WBRestricted`), counts only from a WorkBuddy candidate (`restrictedRefused`, `isWorkBuddy`), as another vendor's 11140 is its own. Bare "request illegal" isn't matched. WorkBuddy's 11128 channel refusal stays `promptRefused` and rests nobody. The Routing page names it "account restricted by the vendor", says the appeal is the way back, and gives the account's row a button that lifts the rest (`/api/gateway/unrest`) once the vendor has. Every other rest a key or account takes (quota, rate limit, retry-after, a failure's backoff) can be lifted by hand the same way (#1869): "Try now" on its row on the Routing page and beside its rest note in the provider's key list. It ends the rest, and with Sink on puts the key back from the back of the order; the backoff count stays, and a refusal after it rests the key again the usual way. Every lift before its time (Try now, `UnrestAll` for a replaced key, `renewed` for windows that renewed) is noted by its rest key (`restingUntil.lifted`) and handed to the Routing page in the trace (`TraceState.Lifted`, `lifted` in `/api/gateway/trace`), and a lift wakes a page waiting on the trace though no route changed (`trace.lifted`). The page stops showing a rest or a sink found before its lift, wherever the lift was asked for (zoecats on Discord: Try now in the provider's editor left Routing at 429 until a restart; `TestTryNowToldToTheRoutingPage`, `routing-lifted-elsewhere.test.cjs`). With another magpie serving the gateway, Try now lifts nothing (#3555). The vendor's safety filter refusing a reply rests nobody, whether it refuses the turn before any of the reply is said or once some of it has been said (`refused`, `refusedAfter`). So does one said in a stream a client is answered whole from (a Codex account is streamed upstream for a `stream:false` Responses, Chat or Messages request): each decoder gives the refusal's error event status 400 and its code (`filterRefused`), a whole reply it cut is answered the refusal rather than its words so far, and Anthropic's error shape, which has no code, carries it in `refusedHeader`; before, it was answered 502 `api_error`, asked again, and each account rested (#3274). `restAfterMarked` itself rests nobody, and counts no failure, for a 400 whose error object `policyRefusal` reads as a refusal, by its code, never by words a body may echo of the request. Its note on the try (and in the error the agent gets when nobody is left) is the vendor's reason, with Anthropic's `stop_details` category and explanation when it gave them (`refusedDetail`, #1768: "safety filter: refusal (category cyber)"); none is made up when it gave none. `stop_details` is carried through the IR (`Event.StopDetails`), so a Claude subscription run through the claude CLI and a translated Anthropic route keep it for an Anthropic client too. How many more candidates a refusal before any of the reply is asked of is Settings' `RefusalRetries` (`refusalAsksAgain`, counted per request in the candidate loop; a group's other members count too): unset, every one left (#248); 0, none (#1925, DD on Discord). When nobody is left, an agent on Anthropic's Messages API gets the held refusal itself, the vendor's 200 with `stop_reason` `refusal` and its `stop_details`, streamed or whole (`holdWriter.handBack`), since that is what Claude Code switches to its fallback model on; a 400 is only an API error to it. Codex and Chat clients still get `failTo`'s 400 (`refusedStatus`), which they don't ask again for. `TestRefusalRetries*` in [`refusal_retries_test.go`](../../internal/gateway/refusal_retries_test.go) cover keys, a group and the Claude subscription. The ChatGPT backend's 502 "response protection is unavailable" is about the request's content, not the account: the same history fails the same on each of its accounts and models. It rests nobody, isn't tried again after a moment, and isn't asked of the provider's other accounts or models; another provider left in a group is asked once (`protectionRefused`, `elsewhere`). One cause is known (#1270): a history that replays the backend's own `web_search_call` in a request that doesn't declare the `web_search` tool is refused so, whatever the account, model or turn (a plain turn, a thread's description, a compaction, Codex's own text compaction for a custom provider with `tools: []`). Every request to the ChatGPT backend with such a history therefore declares cached-only search (`{"type":"web_search","external_web_access":false}`, `provider.DeclareSearch`): an account's in `codexBody`, Codex's own sign-in relayed in `codexUpstreamOn`. It goes in the tools, or for Responses Lite (its header, `reasoning.context` `all_turns`, or an `additional_tools` item already there), which refuses a top-level `web_search`, in the `additional_tools` item. A request that offered no tools gets `tool_choice` `none` so the model can't search; one with a forced choice keeps it. A history without a search, or a request that declares search already, is relayed unchanged; Codex's own `web.run` (a function in the `web` namespace, which Codex offers in place of the hosted tool on a Responses Lite model or with its standalone web search on, and runs through `/alpha/search`) counts as declaring it, since the backend refuses a request carrying both `web.run` and the hosted `web_search` (Savin on Discord, Codex 0.163.0-alpha; `TestSearchedConversationUnderWebRun`). siwc, API-key requests to openai.com and the legacy `/responses/compact` are left as they were. Command Code turning a model away for its Zero Data Retention setting (its plugin's switch, 0.1.14, which sends `x-cmd-zdr: 1`; magpie-community/plugins#246) is a refusal of that request's setting, not of the model or the account: the Provider API's 422 with `"code":"cmd_zdr_no_providers"` and the 400 the plugin makes of Go's error line with `"type":"cmd_zdr_no_providers"` (`zdrCoded`, matched as the error's code or type, never by its words, whose "…a different model.","type":"invalid_request_error" read as a model unserved and rested the model on the account). `keepRetry` notes it beside the error (`zdrHeader`), since the error the agent gets may keep no code (Anthropic's shape, or the 400's numeric code). It rests nobody, anywhere (`restAfterMarked` returns `by: "off"`), so the model answers as soon as the switch is off; it isn't asked of the provider's other accounts at that model, which carry the same header (`notMates`), nor again after a moment; another member, the provider's other models among them, is asked once, and with none left the agent gets Command Code's words (`TestCommandCodeZDRRefusalRestsNothing`, `TestZDRRefusalNeverRests`). Another vendor's refusal in the same words, without the code, still rests the model (`TestZDRRefusalIsCommandCodesCodeOnly`).5. The last candidate's error reaches the agent, with one exception for a group (#1418, `patience.go`). When every member has failed in a way that passes (`busy`: 408, 500, 502, 503, 504 or 529 that isn't a proxy, a quota, response protection, or an upstream that answered a stream request with a whole reply, which fails the same however often it is asked (`didNotStream`; the same-one retries of `passing` leave it alone too, `TestStreamlessMemberIsAskedOnce`), or a 429 that is a short rate limit, not a plan or credit), and nothing of the reply has been sent, the members that failed so are asked again in turn after a pause (`replan`). The pause is `retryPause` doubled each round up to `replanLongest()` (30 times `retryPause`, 30s), and never shorter than the soonest Retry-After; a member whose Retry-After ends past the pause is asked after the others. This goes on while the group's `Patience` lasts. A member of a group in the group uses the innermost that sets `Patience` (`innerPatience`, #2410), as FirstToken (#2246) and Sink (#2255) do; unset falls back to the group asked for, and an inner `PatienceOff` skips replan for that member (`TestNestedGroupPatienceThroughOuter`, `TestNestedGroupPatienceInnerOff`, `TestNestedGroupPatienceFallsBackToOuter`). `replanRounds` (12) is only a backstop that never comes first: the pauses alone add up to `PatienceLongest` in 11 rounds (with 6, a group set to 240s gave up after 90s of pauses, real-jacket on #1418; `TestPatienceIsUsedUp`). The budget is the group's `Patience`, counted from the first time every member had failed, when the agent would have had the error (`waitFrom`; `Group.Waits`: 0 is `PatienceDefault`, 60s; -1, `PatienceOff`, turns it off; at most `PatienceLongest`, 240s). A pause that would end past the budget isn't taken, and the agent gets the error. While another member is busy too, the last one isn't first tried again alone (`passing`): the members take turns, and once the budget has begun, the same-one retries aren't taken either. While the budget lasts, the last candidate's failure is held (`newHoldWriter`), and a streaming agent is kept alive through the pause with SSE comments (`pauseAlive`). The try is traced with `Again` (the pause), `Replan` (how many are asked again) and `Patience` (the budget in seconds). The group editor's "Every member busy" row sets it. A plain provider keeps only the same-one retries `passing` gives the last one left. An agent that goes away in either pause (the same-one retry's or a group's replan) ends the request there with 499: nobody is asked again, and the try whose pause it was is marked `Gone` (#1894, heng91: a relay down while its proxy was off, the agent's window closed). The Routing page says the agent canceled the request before the retry and lists it as canceled, rather than ending its story on "tried again in 2s", a retry that never came (`TestAgentGoneInTheRetryPause`, `routing-agent-gone.test.cjs`). A try that answered is recorded (`served`, `answered`) for routing, affinity and usage. A try is added to the route's `Tries` only as it is asked, so a later try is the record that the gateway went on from this one, and the Routing page tells what came of a try from that, never from where it stood in the order (#2281, xishuchkui-code: an Antigravity 502 empty reply that went on to the next account was told as "an error another account wouldn't fix, so Claude Code gets it"). The one case the record can't show is the last try left out of its allowance after an earlier failure that wasn't one, where the agent is told the earlier error: that try is marked `Earlier` (`routing-went-on.test.cjs`).## Constraints and failure behaviordiff --git a/internal/gateway/fallback.go b/internal/gateway/fallback.goindex b88c1efbd..e3f6342d3 100644--- a/internal/gateway/fallback.go+++ b/internal/gateway/fallback.go@@ -1817,7 +1817,7 @@ func (h *holdWriter) pass() {}dst := h.w.Header()for k, v := range h.header {- if k != resetsHeader && k != refusedHeader && k != zdrHeader { // magpie's own notes, for restAfter and settle+ if k != resetsHeader && k != refusedHeader && k != zdrHeader && k != answeredThereHeader { // magpie's own notes, for restAfter and settledst[k] = v}}@@ -2222,7 +2222,7 @@ func (h *holdWriter) keepAlive() {}dst := h.w.Header()for k, v := range src {- if k != resetsHeader && k != refusedHeader && k != zdrHeader && k != "Content-Length" {+ if k != resetsHeader && k != refusedHeader && k != zdrHeader && k != answeredThereHeader && k != "Content-Length" {dst[k] = slices.Clone(v)}}diff --git a/internal/gateway/gateway.go b/internal/gateway/gateway.goindex 6380e9e82..d5b88e953 100644--- a/internal/gateway/gateway.go+++ b/internal/gateway/gateway.go@@ -2768,6 +2768,7 @@ func (s *Server) serve(w http.ResponseWriter, r *http.Request, from provider.Pro// reconnects are told so again, not sent on to a vendor that// just refused itheld, call.Status, call.Error = true, http.StatusForbidden, said+ noteMember(hw, r, c.p, c.model)writeError(hw, from, call.Status, said)} else if rested, back, ok := quotaHeld(cands[i:]); ok && last {// it rests out of its allowance, and so does every key that@@ -2778,6 +2779,9 @@ func (s *Server) serve(w http.ResponseWriter, r *http.Request, from provider.Pro// told to ask then rather than at oncemsg := fmt.Sprintf("%s (out of its allowance: not asked again before %s)", rested.said, heldClock(back, time.Now()))held, heldBack, call.Status, call.Error = true, back, rested.Status, c.p.Name+": "+msg+ // the answer names who held it, as one asked would: a magpie+ // using this one rests that model of it alone (remoteModelRest)+ noteMember(hw, r, c.p, c.model)writeError(hw, from, call.Status, msg)} else {// a stream that fails before anything is said is let go atdiff --git a/internal/gateway/remote_magpie_key_limit_test.go b/internal/gateway/remote_magpie_key_limit_test.goindex 653932c49..41e0584a5 100644--- a/internal/gateway/remote_magpie_key_limit_test.go+++ b/internal/gateway/remote_magpie_key_limit_test.go@@ -101,3 +101,95 @@ func TestRemoteMagpieKeyLimitRestsTheKey(t *testing.T) {t.Error("a provider that isn't a remote magpie rests the model on a quota refusal")}}++// lagrangepoint1813 on Discord: another computer's magpie added as an+// OpenAI-compatible provider of its own name, not the Remote magpie+// preset, said its Claude Code was out of its session limit, and every+// model of it was refused here with that 429 for the five hours it+// named, whichever one Pi was switched to. A reply that came from a+// magpie (it names the provider that answered, providerHeader) is that+// magpie's model's, whatever the provider here was added as.+func TestAnotherMagpieAddedByHandRestsTheModel(t *testing.T) {+ t.Run("asked there", func(t *testing.T) { anotherMagpieAddedByHand(t, false) })+ t.Run("held there", func(t *testing.T) { anotherMagpieAddedByHand(t, true) })+}++func anotherMagpieAddedByHand(t *testing.T, held bool) {+ clineRestsCleared(t)+ spent := `{"type":"error","error":{"type":"rate_limit_error","message":"You've hit your session limit · resets 8:10pm (America/Los_Angeles)"}}`+ cc := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {+ io.Copy(io.Discard, r.Body)+ w.Header().Set("Content-Type", "application/json")+ w.WriteHeader(http.StatusTooManyRequests)+ io.WriteString(w, spent)+ }))+ t.Cleanup(cc.Close)+ var asked atomic.Int32+ q := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {+ io.Copy(io.Discard, r.Body)+ asked.Add(1)+ w.Header().Set("Content-Type", "application/json")+ io.WriteString(w, `{"id":"c1","object":"chat.completion","model":"fast","choices":[{"index":0,"message":{"role":"assistant","content":"hello"},"finish_reason":"stop"}],"usage":{"prompt_tokens":3,"completion_tokens":1}}`)+ }))+ t.Cleanup(q.Close)+ t.Setenv("XDG_CONFIG_HOME", t.TempDir())+ t.Setenv("XDG_CACHE_HOME", t.TempDir())+ for _, p := range []provider.Provider{+ {ID: "cc", Name: "Claude Code", Key: "k1", Models: []string{"claude-opus-5-5"}, Anthropic: cc.URL},+ {ID: "qd", Name: "Qoder", Key: "k2", Models: []string{"fast"}, Chat: q.URL},+ } {+ if err := provider.Save(p); err != nil {+ t.Fatal(err)+ }+ }+ remote := httptest.NewServer(New().Handler())+ t.Cleanup(remote.Close)+ // as it is added by hand: an OpenAI-compatible endpoint, a key, the+ // other magpie's model ids+ if err := provider.Save(provider.Provider{ID: "rm", Name: "Remote Magpie", Key: "k3", Chat: remote.URL + "/v1",+ Models: []string{"cc/claude-opus-5-5", "qd/fast"}}); err != nil {+ t.Fatal(err)+ }+ send := func(model string) *httptest.ResponseRecorder {+ t.Helper()+ req := httptest.NewRequest("POST", "/v1/chat/completions", strings.NewReader(`{"model":"`+model+`","messages":[{"role":"user","content":"hi"}]}`))+ rec := httptest.NewRecorder()+ New().Handler().ServeHTTP(rec, req)+ return rec+ }+ if held {+ // the other magpie already holds Claude Code, refused twice+ // there, and answers it without asking: its answer names the+ // provider all the same+ for range 2 {+ send("cc/claude-opus-5-5")+ }+ if rec := send("cc/claude-opus-5-5"); !strings.Contains(rec.Body.String(), "not asked again") {+ t.Fatalf("the other magpie asked Claude Code again: %d %s; want it held there", rec.Code, rec.Body.String())+ }+ }+ if rec := send("rm/cc/claude-opus-5-5"); rec.Code != http.StatusTooManyRequests {+ t.Fatalf("Claude Code out of its session limit there: %d %s; want its 429", rec.Code, rec.Body.String())+ }+ rec := send("rm/qd/fast")+ if rec.Code != http.StatusOK || !strings.Contains(rec.Body.String(), "hello") {+ t.Fatalf("Qoder there, after Claude Code's 429: %d %s; want Qoder's answer", rec.Code, rec.Body.String())+ }+ if asked.Load() != 1 {+ t.Errorf("Qoder was asked %d times; want once", asked.Load())+ }+ if rec := send("rm/cc/claude-opus-5-5"); rec.Code != http.StatusTooManyRequests {+ t.Fatalf("Claude Code asked again: %d %s; want its 429", rec.Code, rec.Body.String())+ }+ if rec := send("rm/cc/claude-opus-5-5"); rec.Code != http.StatusTooManyRequests || !strings.Contains(rec.Body.String(), "not asked again") {+ t.Errorf("Claude Code asked again while it rests: %d %s; want its 429 held here", rec.Code, rec.Body.String())+ }+ // held here now, Claude Code holds nothing else of that magpie's+ rec = send("rm/qd/fast")+ if rec.Code != http.StatusOK || !strings.Contains(rec.Body.String(), "hello") {+ t.Fatalf("Qoder there, while Claude Code is held here: %d %s; want Qoder's answer", rec.Code, rec.Body.String())+ }+ if asked.Load() != 2 {+ t.Errorf("Qoder was asked %d times; want twice", asked.Load())+ }+}diff --git a/internal/gateway/routing.go b/internal/gateway/routing.goindex c90c89a01..ac58fb611 100644--- a/internal/gateway/routing.go+++ b/internal/gateway/routing.go@@ -1177,9 +1177,14 @@ func (s *Server) restAfterMarked(c candidate, status int, header http.Header, bo// the refusal is read whoever answered). Its key refused, or the computer// unreachable, still rests it whole, and so does the key's own limit there// (keyLimited's 429, with remoteKeyLimitHeader), which refuses every model-// alike (#2077).+// alike (#2077). A magpie added by hand, as an OpenAI-compatible provider+// of its own name, is one all the same: its reply names the provider that+// answered there (providerHeader, which keepRetry notes as+// answeredThereHeader), as no vendor's does (lagrangepoint1813+// on Discord: "Remote Magpie: Claude Code: You've hit your session+// limit" answered every model of it for the five hours it named).func remoteModelRest(c candidate, why string, header http.Header) bool {- if !c.p.IsRemoteMagpie() || header.Get(remoteKeyLimitHeader) != "" {+ if !c.p.IsRemoteMagpie() && header.Get(answeredThereHeader) == "" || header.Get(remoteKeyLimitHeader) != "" {return false}return why == failQuota || why == failCredit || why == failRate || why == failRestricted || why == failVerify@@ -1357,6 +1362,12 @@ func keepRetry(dst, src http.Header, body []byte) {dst.Set("Retry-After", strconv.Itoa(int(d.Seconds())))}}+ if who := src.Get(providerHeader); who != "" {+ // another magpie refused it, naming its provider that did: this+ // magpie's own name for the provider goes in the same header+ // (noteMember), so it is noted beside it, for restAfter+ dst.Set(answeredThereHeader, who)+ }if note, ok := policyRefusal(body); ok {// the error the agent gets keeps the vendor's words but not its// code (bio_policy): that it was the safety filter goes on beside@@ -1370,6 +1381,11 @@ func keepRetry(dst, src http.Header, body []byte) {}}+// answeredThereHeader carries, from keepRetry to restAfter, the provider+// another magpie named on its refusal (providerHeader): the refusal is+// that magpie's model's (remoteModelRest).+const answeredThereHeader = "X-Magpie-Answered-There"+// refusedHeader carries, from keepRetry to settle, that an error status// was the safety filter refusing the request, and what it said.const refusedHeader = "X-Magpie-Refused"