Every agent's model. One place. Codex on DeepSeek, Claude Code on Kimi, from the menu bar.
gateway: the request archive doesn't put an unmasked route back on masking (#3973)
yetone7fcf642eedf8
diff --git a/docs/subsystems/gateway-routing.md b/docs/subsystems/gateway-routing.mdindex 023bccc09..25d848913 100644--- a/docs/subsystems/gateway-routing.md+++ b/docs/subsystems/gateway-routing.md@@ -137,7 +137,7 @@ recorded as a prediction failure (`noPrediction`).## Runtime path1. `handle(proto)` reads the body and the model (`requestBody`, `requestModel`), then calls `serveAgent`. Every route that reads an agent's body (each API, count_tokens, Gemini's, embeddings, images, videos, System One, the Codex backend path) reads it through `readBoundedRequestBody` in [`request_bounds.go`](../../internal/gateway/request_bounds.go). It decodes a `Content-Encoding` of `gzip` or `zstd` (`decodedBody`; Codex sends zstd to a custom provider's `/v1/responses` too, #1223) and drops the header, so the provider is sent plain JSON, with one exception: a ChatGPT account's turn (POST `CodexBase`/responses, from the accounts loop in `forwardOnce` or relayed by `codexUpstreamOn`) is compressed again with zstd and a window of at most 2 MiB, as Codex's own client sends it (`provider.CodexCompressed`; openai/codex `responses_request_compression` and `http-client/src/request.rs`). It is compressed once the body is final, and again on each try. `/responses/compact`, an API key's requests and every other provider stay plain. Sent plain, a 1.1 MB text-only turn was answered 503 (ylorn on X). The plain body is what magpie keeps and shows, and `codexDropped` judges a reset by the bytes that went on the wire. `codexDropped` also reads Envoy's 507 "exceeded request buffer limit while retrying upstream" (the backend failed and the front couldn't retry a body that large) as that reset, at any size, told as a 503 so magpie, Codex and pi ask again and nobody rests (#2034). The size limit (`defaultBodyLimit`, 512 MB) holds for the decoded bytes (413), and any other encoding is refused 415. It was 128 MB until a long Codex session that had read many images went past it decoded, its inline screenshots resent each turn, and got the 413 on all five of Codex's retries (#1422, `TestImageHeavyCodexTurnIsRead`). magpie's own 413 says it is magpie's gateway limit, with the size, and that the provider was not asked (`overLimit`); `writeError` adds to any 413 it isn't holding that this is a byte limit, not the model's context, and to `/compact` or start a new conversation (`TestOverLimitSaysWhoseAndWhatToDo`). Every shape but Gemini's types a 413 `request_too_large`, Anthropic's own type, which pi's overflow table knows: pi compacts and tries once more rather than stopping on an OpenAI-shaped `api_error` (@wilsonxuuuu on X, `TestPayloadTooLargeSaysRequestTooLargeToPi`). `keyLimited` reads a limited key's compressed body the same way, so its reservation is the decoded size. `serveAgent` runs the [middleware](gateway-middleware.md) chain, then `serve`.-2. `serve` redacts secrets in the request (`redacted`; `redact.MaskJSON` leaves ids alone, and in any text a backend's id (a UUID, 32 hex digits or more, or a digest of 16 to 31 hex digits in one case with letters and digits both, a cache key or a short commit, which went as a key before: _kaichen on X, 10-28; `digestShaped`), or an element token cua-driver hands the model for computer use (`s0000002a:14`, #3782), goes as written: no rule, model label or value known from before masks a piece of one (a phone number at the end of `…-a13800138000`, a card number across a UUID's groups), and a whole one is masked only by the user's own words and rules or as a credential, by the password, API key and token rules or a secret rule whose field is named for one (`api_key=`, `refresh_token`), never one named for an id, a cursor, a request or a digest (`secret_id`, `next_page_token`, `Idempotency-Key`, `secret_hash`), nor cua-driver's own `element_token` (any other name with `element` in it, `element_api_key`, is a credential's as before), a bare `key` (not after api, access, secret, private, signing or license: `keyPhrase`), a field named for a cache, commit, object, blob, file, content, revision, partition, shard, bucket, dedup, lookup, row or sort key, a serial number, or what the model takes a UUID or an element token for, nor an element token known from before (one the model labelled in prose a turn earlier) (`noIDs`, [`internal/redact/ids.go`](../../internal/redact/ids.go)); and a tool's name and its MCP server's (`namespace`, `server_label`, `server_name`, #3143); the request's tool definitions and output schemas, found by their place in each protocol (top-level `tools`, `tool_choice`, `response_format`, `text`, `generationConfig`, `stream_options`, the client's ids in `client_metadata` and the like, and the tools of a Responses `additional_tools` or `tool_search_output` item), go as written save their descriptions, so a word the user masks can't break a grammar or an enum (#1911); and what the vendor sealed with a signature, a thinking block, Gemini's thoughts or Responses' encrypted reasoning, goes back as the vendor wrote it: only the values masked elsewhere in the request, and secrets masked before, are put back as their placeholders; a value masked once, at least 8 characters long, is masked again wherever a request has it, as an exact match whatever words are around it, so what the vendor wrote about a placeholder doesn't go back with the value in it, `redact/known.go`; a text masked for a vendor before, such as a system prompt or a turn already sent, is masked as it was then, so a value a rule first finds later in a conversation doesn't change the prompt the vendor has cached and rewrite all of it to the cache, `sentKnownSpans`), resolves the model to a provider or a group, and refuses what can't be served. The reply has the values put back on its way to the agent (`redact.Writer`, a stream event by event, a whole body at its end): a placeholder the model wrote as it was given, or as models rewrite one (spaces inside the braces, a brace or both dropped, another case), is the value again when what is left names one magpie made, and one split across events is held until it is whole (`redact.Restore`, `partialTail`, [`internal/redact/redact.go`](../../internal/redact/redact.go)). A request whose provider and fallbacks, or whose group's models, all skip redaction (`unredactedRoute`, `provider.SkipsRedaction`: set *Send requests unmasked*, `Unredacted`, with every address on this machine or the local network) goes to them as the agent wrote it, and is masked only for a body an observer wants or the request archive keeps, which may go elsewhere (`bodiesKeptAway`); without those it isn't masked at all, and the log and recent calls keep it as it went, since a request is masked only once its route is known (#3973: masking a body whose masked copy was thrown away took up to minutes of magpie's own time). A request turned away before it is routed is logged masked (`maskedCopy`). count_tokens and embeddings follow the same rule. What a routing group's Jev is told of the turn (the message, the user's message before it and the reply to it) is masked all the same unless Jev's own provider skips redaction too (`maskedState` in `askJev`, [`decide.go`](../../internal/gateway/decide.go)): a remote Jev is none of the group's members. The masking is the built-in plugin `redact`'s (`gwmw.Masker`, [Plugin runtime](plugin-runtime.md)); when the settings ask for masking and no masker serves, or it fails, the request is a 503 and nothing is sent (`redacted`, `gwmw.Masking`).+2. `serve` redacts secrets in the request (`redacted`; `redact.MaskJSON` leaves ids alone, and in any text a backend's id (a UUID, 32 hex digits or more, or a digest of 16 to 31 hex digits in one case with letters and digits both, a cache key or a short commit, which went as a key before: _kaichen on X, 10-28; `digestShaped`), or an element token cua-driver hands the model for computer use (`s0000002a:14`, #3782), goes as written: no rule, model label or value known from before masks a piece of one (a phone number at the end of `…-a13800138000`, a card number across a UUID's groups), and a whole one is masked only by the user's own words and rules or as a credential, by the password, API key and token rules or a secret rule whose field is named for one (`api_key=`, `refresh_token`), never one named for an id, a cursor, a request or a digest (`secret_id`, `next_page_token`, `Idempotency-Key`, `secret_hash`), nor cua-driver's own `element_token` (any other name with `element` in it, `element_api_key`, is a credential's as before), a bare `key` (not after api, access, secret, private, signing or license: `keyPhrase`), a field named for a cache, commit, object, blob, file, content, revision, partition, shard, bucket, dedup, lookup, row or sort key, a serial number, or what the model takes a UUID or an element token for, nor an element token known from before (one the model labelled in prose a turn earlier) (`noIDs`, [`internal/redact/ids.go`](../../internal/redact/ids.go)); and a tool's name and its MCP server's (`namespace`, `server_label`, `server_name`, #3143); the request's tool definitions and output schemas, found by their place in each protocol (top-level `tools`, `tool_choice`, `response_format`, `text`, `generationConfig`, `stream_options`, the client's ids in `client_metadata` and the like, and the tools of a Responses `additional_tools` or `tool_search_output` item), go as written save their descriptions, so a word the user masks can't break a grammar or an enum (#1911); and what the vendor sealed with a signature, a thinking block, Gemini's thoughts or Responses' encrypted reasoning, goes back as the vendor wrote it: only the values masked elsewhere in the request, and secrets masked before, are put back as their placeholders; a value masked once, at least 8 characters long, is masked again wherever a request has it, as an exact match whatever words are around it, so what the vendor wrote about a placeholder doesn't go back with the value in it, `redact/known.go`; a text masked for a vendor before, such as a system prompt or a turn already sent, is masked as it was then, so a value a rule first finds later in a conversation doesn't change the prompt the vendor has cached and rewrite all of it to the cache, `sentKnownSpans`), resolves the model to a provider or a group, and refuses what can't be served. The reply has the values put back on its way to the agent (`redact.Writer`, a stream event by event, a whole body at its end): a placeholder the model wrote as it was given, or as models rewrite one (spaces inside the braces, a brace or both dropped, another case), is the value again when what is left names one magpie made, and one split across events is held until it is whole (`redact.Restore`, `partialTail`, [`internal/redact/redact.go`](../../internal/redact/redact.go)). A request whose provider and fallbacks, or whose group's models, all skip redaction (`unredactedRoute`, `provider.SkipsRedaction`: set *Send requests unmasked*, `Unredacted`, with every address on this machine or the local network) goes to them as the agent wrote it and isn't masked on its way, since a request is masked only once its route is known (#3973: masking a body whose masked copy was thrown away took up to minutes of magpie's own time). The log, recent calls and the request archive keep it as it went (the archive's bodies have their secrets taken out, `redact.ScrubJSON`, as every call's do), whether the archive is on or off; an observer that wants the bodies (the OTLP export, a JS plugin's) is handed it masked, masked once when it is first handed it after a try (`Call.maskIn`, `laterMasked`), never before the request is sent. A request turned away before it is routed is logged masked (`maskedCopy`). count_tokens and embeddings follow the same rule. What a routing group's Jev is told of the turn (the message, the user's message before it and the reply to it) is masked all the same unless Jev's own provider skips redaction too (`maskedState` in `askJev`, [`decide.go`](../../internal/gateway/decide.go)): a remote Jev is none of the group's members. The masking is the built-in plugin `redact`'s (`gwmw.Masker`, [Plugin runtime](plugin-runtime.md)); when the settings ask for masking and no masker serves, or it fails, the request is a 503 and nothing is sent (`redacted`, `gwmw.Masking`).- With *Mask personal data* on, each kind in `redact.Categories` ([`internal/redact/more.go`](../../internal/redact/more.go)) is masked unless the user turned it off (`redactKinds` in settings, `Options.Kinds`). On by default: US SSNs, passport numbers, IBANs that pass mod 97, birthdays next to a word that says so (a date over a year ago: one in the last year or ahead is the day an agent runs on, `dateOK`); the word must be right before the date, so a log line's or a file name's date is none, and a time beside the date doesn't make it a log's: a date of birth stored as a time (`1990-05-11T16:00:00.000Z`) is one (`TestBirthdayLogDates`; #3878), MAC addresses, and serial numbers next to S/N or the like. Eleven digits from 13 to 19 are a mainland mobile's form and an id's too, so they are a phone only with +86 or 86 before them, as the value of a field whose name says phone (phone, mobile, tel, cell, contact, 手机, 电话, a field named `number`), or in prose with no id's word right before them (order, id, no., #, 订单号, 编号, 单号, 流水号); under order_id or uid, after 订单号, or with a letter or digit against them they go as written (`phoneAt` in [`internal/redact/phone.go`](../../internal/redact/phone.go); _kaichen on X, 10-28). Off by default: the user name in a home folder, user@host in a prompt or ssh command, public IPv4 and IPv6 addresses (never private, loopback, link-local, CGNAT or documentation ranges) and cloud bucket names, since agents send them in nearly every request and the model must copy the placeholder exactly inside a path or URL. When the user name is on, it goes as a made-up name of 8 lowercase letters, the same for that name every turn and put back in replies like any placeholder (`standIn` in [`shape.go`](../../internal/redact/shape.go)), not as `{{USERNAME_…}}`: with mimo-v2.6-flash a model read `C:\Users\{{…}}` as a temporary folder and set out to delete it (eerttreeeert on X, 10-28). Context rules run only near their words (`rule.matches`). What reads as an address but ends in a file's extension that no domain has (`…@2x.jpg`, `[email protected]`; `fileExt` in `realEmail`), or a scale before an extension that is a domain too (`[email protected]`, `[email protected]`; `scaleExt`), is a file's name, for the rule and the local model alike (#3029). `[email protected]` is still an address. The Settings rows come from `REDACT_KINDS` in app.js, which `TestRedactKindsAreRedacts` holds to the same ids and defaults.- With *Find with a local model* on (`settings.RedactModel`, this computer's own, kept by `KeepOwn`), a local model finds what no rule can, a name or an address in free text, under the same switches: a name, address, phone, email or account number is personal data, a secret a secret (`modelKinds`, `modelSpans` in [`internal/redact/model.go`](../../internal/redact/model.go)). `MaskJSON` asks it once per request, for every text it would mask, each once (`withModel`); its spans join the rules' with a rule's kind kept where both find a value, and ids a vendor or tool made (`req_…`, `toolu_…`) are never taken, nor a snake_case word as a name (Codex's `sequential_cutoff`, #3144), nor as a secret what names a thing: a UUID, a digest with its algorithm's name, a file's path (`namesThing`; the model takes all three for secrets). The model misses many Chinese names (张伟 after 给, 陈建国 after 客户, however low its threshold) and runs a name it finds on into the words after it (「王芳,她下周一」), so with it on a Chinese name is also found by its surname and a word around it that says a person is meant (客户, 我叫, 给…发, …先生, …说, joined by 和 to another name; 和 or 与 says so only after a person, 吴敏和郑浩 but not 判断和边界, 发 or 打 only as the verb, 发了个 but not 关键发现, and a sentence starts after punctuation, not after a space after code, `gh pr view` 易触发; xuanwo on X; 一下 only after a verb that asks a person, 问一下张伟 but not 改一下文案, a word any subject takes after it, 已经, 明天 or 他, only with a person's cue before it, and 说明 is no 说; zeewell on X), and the model's are cut at punctuation and titles ([`zhname.go`](../../internal/redact/zhname.go)); a surname with nothing around it (王国的, 张开的) is left, and so is a common word that starts with one (`zhWords`: 文案, 文档, 方案; 毛利, 毛重, 毛巾, since 毛利 is a margin far more often than the Japanese surname, so 毛利低 goes as written: _kaichen on X, 10-28; the model still finds 毛利兰, and neither model nor rule masks 毛利小五郎), the model's own name too when it is that word whole. The model is the user's pick (`settings.RedactModelName`, `pii.Choose`; the app's menu beside the switch, `pmPick`): AstrLink Guard (QuantumNous/astrlink-guard at a pinned revision, Apache-2.0, a 39 MB int8 Multilingual-MiniLM token classifier for Chinese and English), run in magpie's own process on the CPU by [`internal/pii/guard`](../../internal/pii/guard) (an ONNX reader, the XLM-R tokenizer and int8 kernels in Go, NEON/SDOT on arm64 and SSE2 on amd64; its labels named as Privacy Filter's, `guardLabels`), and on a Mac through CoreML on the Neural Engine or the GPU ([`coreml.go`](../../internal/pii/guard/coreml.go), [`internal/pii/guard/coreml`](../../internal/pii/guard/coreml); yyhhyyyyyy on X): the same network from the same int8 weights in float16, written from the downloaded model into a program made by `coreml_gen.py` and compiled once into the model's folder, 512 tokens in about 12 ms where the CPU takes 400, its probabilities within .07 of the publisher's fp32 model where the CPU's are within .13 (the CPU quantizes activations as the int8 model does, CoreML doesn't), so a span near the threshold can fall the other side (a go.mod module path is a secret at .81 on CoreML, .79 on the CPU, .785 in fp32); a window under 16 tokens (`coremlMin`), a Mac before macOS 13 or any failure goes to the CPU, loaded on the first request and let go after 10 minutes with none; or OpenAI's Privacy Filter. With no pick it is AstrLink Guard, the default; a user who had Privacy Filter on before there was a choice keeps it only while AstrLink Guard downloads, which the first masked request starts and which then saves AstrLink Guard as the pick (`masking.picked`, `toGuard`; an hour between tries after a failure). Measured for that default (#3578): on 234 segments of real code and config it found 2 spans where Privacy Filter found 100 (38 of them go.sum hashes after redact's own checks), and with the rules it found 42 of 42 test values to Privacy Filter's 41. Each model has its own download, cache file and turn (`backend`). Both find at a floor of 0.5 (`pii.Floor`) and give each span its score (AstrLink Guard: the least of its tokens' probabilities, rounded to a float32 so a cached span reads back the same; Privacy Filter: pf-serve's own), and masking keeps those at the model's threshold or over (`pii.Threshold` in `masking.model`): the user's for that model (`settings.RedactModelScore`, this computer's own; Settings → Privacy's Confidence threshold, `pmScore`, 0.5 to 0.95), else the model's own (`MinScore`: Privacy Filter 0.5, AstrLink Guard 0.8, its publisher's). A value known from before follows the same threshold: each value masked remembers the highest score anything found it with (a rule's counts as sure), and one only the model found, under the threshold now, is no longer masked again as known (`noteScores`, `knownSpans` in [`known.go`](../../internal/redact/known.go); before, a raised slider changed nothing for a value masked once: _kaichen on X, 10-28). The defaults stay because on the eval a higher one mostly loses values the checks after the model would have kept (Privacy Filter at 0.85 lost a Chinese name; AstrLink Guard at 0.9 a phone in a tool result), while the false alarms it would drop are mostly dropped by those checks already (Yayoi_no_yume on X). Measured again on 2000 segments of real agent traffic (Codex and Claude Code sessions: prompts, tool arguments and results, a quarter with Chinese) and 30 more labelled cases: AstrLink Guard at 0.88 rather than 0.8 drops 3 false alarms (a model id, a sandbox path word, a token counter) and lets a colleague's name and a signed name through; Privacy Filter at 0.88 rather than 0.5 drops 11 (timestamps in paths, log lines, a plugin id) and lets 6 real names and a phone through (4 of the names in the real traffic). Lowering Guard to 0.5 finds 2 more names in the real traffic and 3 more labelled values, for 10 more false alarms (9 of them Claude Code's `<total_tokens>` counter). Those false alarms are shapes a check can turn away; a threshold can't without losing real values. Privacy Filter is a q8 GGUF (1.6 GB), run by `pf-serve` ([`native/privacy-filter`](../../native/privacy-filter), built from privacy-filter.cpp on ggml and released under `pf-v*` tags; on a GPU it holds the model once, in the device's memory, #3590; every pf-serve keeps the engine's own MoE chunk, `PF_MOE_CHUNK` at the window's 4096, which an RX 470 through Vulkan read 6-9% faster than 2048 in interleaved runs and Metal ~6% faster, and inherits a value the user set): Settings → Privacy's On downloads both (`pii.Download`, each checked against its pinned sha256, through magpie's proxy (`netproxy.Func`, as its other requests; hh0592821 on Discord, whose download went direct before), from hf-mirror first in China (`source.chinaFirst`) and from hf-mirror after Hugging Face everywhere else, the switch off too (`source.modelMirror`), so a poisoned or blocked huggingface.co doesn't stop it; hf-mirror serves AstrLink Guard's files itself and sends Privacy Filter's back to Hugging Face) and saves the setting only once they are on disk (`/api/privacy-model`, [`privacymodel.go`](../../internal/gui/privacymodel.go)). `pii.Find` starts `pf-serve` on the first request (Metal, Vulkan, else the CPU; one that dies on the GPU, doesn't load there in 40s (`gpuLoadTimeout`, well inside the gateway's 2 minutes), or doesn't answer in time there twice in a row, is started on the CPU, and Settings says why; a request it didn't answer in time once is tried on the GPU again, since a slow request on a weak GPU is no lost GPU (#3682). The GPU is tried again 10 minutes later, doubling to 2 hours while it keeps failing, with no restart (`gpuRetryAfter`), and one that answers is the model's again), joins short texts into 12 KB chunks and maps the spans back, cuts a text over 12 KB into pieces of 12 KB at most that overlap by 1 KB (`pieces`: after a line's end, else a space, else at a rune's start), each kept by its own hash, their spans put back at the text's offsets and merged where pieces overlap (`merge`: one found twice is one, one cut by a piece's end is whole), and asks pf-serve a chunk at a time (#3682: a 480 KB text whole took an RX 470/580 90s and kept nothing when cut off), keeps the last 20000 answers by hash, on disk too (`found-<model>.bin` beside the model: hashes, offsets, labels and each span's score, never text; a `pfound01` file from before scores is read with every span sure, so it masks as it did; written through temp-and-rename, a bad read taken as empty), so a restart doesn't ask the model about every history again (#3682), and ends it after 10 minutes with no request. Its requests take turns on its one pipe (`turn`), and a request reads the cache again when its turn comes; a request waits for its turn only while its context lives (`pii.FindContext`, through `gwmw.ContextTeller`), so one whose client went away leaves the queue (the gateway's 2 minutes leave masking's time out, #3682); the chunk pf-serve is on is finished and kept, so a request sent again asks only about what is left, and between chunks the turn is given up and taken again, so a short request goes before the rest of a long one. The status (`pii.Now`), `pii.Stop` and the idle timer never wait for a load or a request: `srv.mu` is held only to read or set the state, and `Stop` ends a load or a request under way at once. A request held before routing while it waits for the model is answered 504 saying so, and how to send without it (`unroutedMsg`); one of an older tag (`oldTags`, magpie updated since the download) runs until the pinned tag's is fetched (`upgrade`, on its start), which is then started on the next request and the old deleted ([`internal/pii`](../../internal/pii)). A failure names what ended `pf-serve`: magpie's own end of a request it didn't answer in time, else its exit status or signal and its last stderr lines past ggml's startup chatter (`died`, `lastSaid`). After one, requests are held back at once with that failure, not after a load each, until the model is tried again 30s later, doubling to 10 minutes while it keeps failing (`heldBack`, `retryAfter`; lazyeo on Discord, an M2 whose every request waited out the 504). A model that is on and can't answer (not on disk, didn't start, hung, held back) panics, so the request is held back with the 503 above rather than sent with the rules' masking alone (`masking.model`).- With *Mask secrets* on, the user's own masking rules (`redactRules`, `redact.Rule`: a placeholder name and a prefix or an RE2 pattern, [`internal/redact/rules.go`](../../internal/redact/rules.go)) run before magpie's. Settings → Privacy adds them, removes them, and edits one in place (`POST /api/settings/redact-rule` with the rule's index and its current value, `editRedactRule` in [`internal/gui/api.go`](../../internal/gui/api.go)). Every rule is checked by `redact.CheckRules` when settings are saved; an edit that doesn't compile, matches the empty string, repeats another rule or names a rule no longer at that index is refused with the rules left as they were. The masker reads the rules from settings on each call (`options` in [`internal/masking`](../../internal/masking/masking.go)), so a change applies to the next request.diff --git a/internal/gateway/capture.go b/internal/gateway/capture.goindex 968255ae9..ff1d2a707 100644--- a/internal/gateway/capture.go+++ b/internal/gateway/capture.go@@ -155,6 +155,13 @@ func withBodies(rec *usage.Record, c *Call) {if c.wholeIn != nil {in, inCut = string(c.wholeIn), c.wholeInCut}+ if c.maskIn != nil {+ if m := c.maskIn.body(); c.wholeIn != nil {+ in = string(m)+ } else {+ in, inCut = captureRequestBody(m)+ }+ }out, outCut := c.ResponseBody, c.ResponseTruncatedif c.wholeOut != nil {out, outCut = string(c.wholeOut), c.wholeOutCutdiff --git a/internal/gateway/gateway.go b/internal/gateway/gateway.goindex c4a8ecade..70ce3d1a4 100644--- a/internal/gateway/gateway.go+++ b/internal/gateway/gateway.go@@ -405,6 +405,9 @@ type Call struct {// bodies above, which is all the Recent-calls page keepswholeIn, wholeOut []bytewholeInCut, wholeOutCut bool+ // maskIn: the request went as written (unredactedRoute) with masking+ // on, so an observer is handed its body masked here, not as it went+ maskIn *laterMasked}// Server is the gateway.@@ -1701,12 +1704,10 @@ func (s *Server) serve(w http.ResponseWriter, r *http.Request, from provider.Pro// secrets go as placeholders and come back as they were; the log has// what the vendor saw and said. plain is the body as the agent wrote// it, for a request that goes only where the user said it may go- // unmasked (unredactedRoute)// unmasked (unredactedRoute). The body is masked once the route is- // known (below): one that goes as written isn't masked at all, where- // masking it took up to minutes for nothing (#3973)+ // known (below): one that goes as written isn't masked on its way,+ // where masking it took up to minutes for nothing (#3973)plain := body- var masked []byte // the masked body, when plain goes insteadvar maskedHits maskHitsmaskDone, sentWhole := false, falseunmask := func() {}@@ -1941,10 +1942,12 @@ func (s *Server) serve(w http.ResponseWriter, r *http.Request, from provider.Prog, ms, isGroup := provider.FindGroup(asked)g = g.Live() // a manual group's rules wait// a model on this machine or the local network that the user set to- // go unmasked gets the request as written (lc on Discord), and it is- // masked only for an observer or the archive, which may keep it- // elsewhere- if sentWhole = unredactedRoute(p, isGroup, ms) && !bodiesKeptAway(); !sentWhole {+ // go unmasked gets the request as written (lc on Discord), and it+ // isn't masked on its way, the request archive on or not: the archive+ // keeps it as it went, its secrets taken out as every archived body's+ // are, and an observer that wants the bodies is handed a copy masked+ // when it is first handed one, after the try (maskIn, #3973)+ if sentWhole = unredactedRoute(p, isGroup, ms); !sentWhole {rw, b, done, hits, err := redactedHits(r.Context(), capture.ResponseWriter, body)if err != nil { // fails closed: never sent unmaskedlog.Printf("gateway: %v", err)@@ -1953,16 +1956,11 @@ func (s *Server) serve(w http.ResponseWriter, r *http.Request, from provider.Proreturn}capture.ResponseWriter, body, unmask, maskedHits = rw, b, done, hits- if unredactedRoute(p, isGroup, ms) {- masked, body = body, plain- }+ } else if usage.ObservedBodies() != usage.NoBodies {+ call.maskIn = &laterMasked{ctx: context.WithoutCancel(r.Context()), plain: body}}maskDone = true- if masked != nil {- logBody(masked)- } else {- logBody(body)- }+ logBody(body)// a gateway key held to some models (#882) is refused another, or a// group it doesn't name with one it may not use in itkeyWho, keyHeld := keyHolds(r)@@ -2037,9 +2035,6 @@ func (s *Server) serve(w http.ResponseWriter, r *http.Request, from provider.Pro// text (#1613)if b, ok := withoutSealedMessages(body); ok {body = b- if masked != nil {- masked, _ = withoutSealedMessages(masked)- }sealedTask = hasSealedAgentMessage(body)}}@@ -2463,7 +2458,7 @@ func (s *Server) serve(w http.ResponseWriter, r *http.Request, from provider.Pro// request went as written. The record names the provider and model// the last try went to, not the group's first member, which a// failover may never have reached- if masked == nil && !sentWhole {+ if !sentWhole {m, done := noteMaskedUntil(r, "chat", maskedHits, string(body), tr.ID, p.ID, call.Model)if m != nil {s.trace.update(tr, func(t *Route) { t.Masked = m })@@ -2472,11 +2467,7 @@ func (s *Server) serve(w http.ResponseWriter, r *http.Request, from provider.Pro}// the card's text is the masked body, even where the request went// unmasked: masked by PromptText when it went whole (#3973)- textBody := body- if masked != nil {- textBody = masked- }- promptRead := s.inspectPrompt(tr, from, body, textBody, sentWhole)+ promptRead := s.inspectPrompt(tr, from, body, body, sentWhole)var lastTried provider.Provider // the last try's, for its model's context window and the usage's endpointvar skipped []stringsent := "" // the reasoning the last try's model was asked for@@ -3210,7 +3201,7 @@ func (s *Server) serve(w http.ResponseWriter, r *http.Request, from provider.ProfailedWith(&rec, call.Status, call.Error, call.Usage.ErrType)// what this account answered is its refusal, the reply// captured so far being no one's yet- refusal := &Call{RequestBody: call.RequestBody, RequestTruncated: call.RequestTruncated, ResponseBody: string(hw.errBody())}+ refusal := &Call{RequestBody: call.RequestBody, RequestTruncated: call.RequestTruncated, ResponseBody: string(hw.errBody()), maskIn: call.maskIn}if call.wholeIn != nil {refusal.wholeIn, refusal.wholeOut = call.wholeIn, hw.errBody()}@@ -3254,7 +3245,7 @@ func (s *Server) serve(w http.ResponseWriter, r *http.Request, from provider.ProfailedWith(&rec, call.Status, call.Error, call.Usage.ErrType)// what this account answered is its refusal, the reply// captured so far being no one's yet- refusal := &Call{RequestBody: call.RequestBody, RequestTruncated: call.RequestTruncated, ResponseBody: string(hw.errBody())}+ refusal := &Call{RequestBody: call.RequestBody, RequestTruncated: call.RequestTruncated, ResponseBody: string(hw.errBody()), maskIn: call.maskIn}if call.wholeIn != nil {refusal.wholeIn, refusal.wholeOut = call.wholeIn, hw.errBody()}diff --git a/internal/gateway/redact.go b/internal/gateway/redact.goindex 200e5697b..feb413e60 100644--- a/internal/gateway/redact.go+++ b/internal/gateway/redact.go@@ -5,6 +5,7 @@ import ("errors""fmt""net/http"+ "sync""time""github.com/yetone/magpie/internal/gwmw"@@ -12,7 +13,6 @@ import ("github.com/yetone/magpie/internal/maskrec""github.com/yetone/magpie/internal/provider""github.com/yetone/magpie/internal/settings"- "github.com/yetone/magpie/internal/usage")// redacted masks a request's secrets, as the settings say, before it goes@@ -265,16 +265,22 @@ func maskedCopy(ctx context.Context, body []byte) []byte {return b}-// bodiesKeptAway says a request's body may be kept off this computer: an-// observer wants it (the OTLP export, a JS plugin's observer) or the-// request archive is on. A request sent unmasked is masked for them all-// the same.-func bodiesKeptAway() bool {- if usage.ObservedBodies() != usage.NoBodies {- return true- }- _, on := archiveDest()- return on+// laterMasked is the body of a request that went as written, masked the+// first time an observer is handed it (withBodies): after its try, never+// on its way (#3973). nil when masking fails: nothing unmasked is handed+// on in its place.+type laterMasked struct {+ once sync.Once+ ctx context.Context+ plain []byte+ b []byte+}++func (l *laterMasked) body() []byte {+ l.once.Do(func() {+ l.b, l.plain = maskedCopy(l.ctx, l.plain), nil+ })+ return l.b}// unredactedRoute says a request resolved to p, or to the group whosediff --git a/internal/gateway/unmasked_route_test.go b/internal/gateway/unmasked_route_test.goindex c93e2867d..82524ca45 100644--- a/internal/gateway/unmasked_route_test.go+++ b/internal/gateway/unmasked_route_test.go@@ -1,6 +1,7 @@package gatewayimport (+ "encoding/json""net/http""net/http/httptest""strings"@@ -34,22 +35,29 @@ func (c countedMasker) Writer(w http.ResponseWriter) (http.ResponseWriter, func(// unmasked was masked all the same before it was routed, and the masked// body thrown away, up to minutes of magpie's own time for each. Now it// isn't masked at all, a chat or a token count, and the log has it as it-// went; one that goes to a vendor, an unknown model's, or one an observer-// keeps the bodies of is masked as before.+// went; one that goes to a vendor, or an unknown model's, is masked as+// before. With the request archive on it was masked all the same (#3973,+// wangbinyq: 请求归档开启的话, 还是会先走脱敏路径): the archive keeps it as+// it went now. An observer that keeps the bodies is handed them masked,+// masked after the try instead of before it.func TestUnmaskedRouteIsNotMasked(t *testing.T) {const key = "sk-proj-abcdEFGH1234ijklMNOP5678qrst"+ const placeholder = "{{API_KEY_" // the key masked; the archive and an export take it out otherwisechat := `{"model":"fake/m1","max_tokens":10,"messages":[{"role":"user","content":"my key is ` + key + `"}]}`count := `{"model":"fake/m1","messages":[{"role":"user","content":"my key is ` + key + `"}]}`cases := []struct {name stringset boolobserved bool+ archived boolmasks bool // the masker is askedwhole bool // the provider is sent the key}{{name: "set to go unmasked", set: true, whole: true},{name: "unset", masks: true},{name: "an observer keeps the bodies", set: true, observed: true, masks: true, whole: true},+ {name: "the request archive is on", set: true, archived: true, whole: true},+ {name: "the archive is on, unset", archived: true, masks: true},}for _, tc := range cases {t.Run(tc.name, func(t *testing.T) {@@ -63,11 +71,17 @@ func TestUnmaskedRouteIsNotMasked(t *testing.T) {if err := provider.Save(*p); err != nil {t.Fatal(err)}- if err := settings.Save(settings.Settings{Redact: true}); err != nil {+ if err := settings.Save(settings.Settings{Redact: true, RequestArchive: tc.archived}); err != nil {t.Fatal(err)}+ obs := &fakeObserver{watch: true, bodies: usage.CapturedBodies}if tc.observed {- t.Cleanup(usage.Observe(&fakeObserver{bodies: usage.CapturedBodies}))+ t.Cleanup(usage.Observe(obs))+ }+ bucket := &memBucket{objs: map[string][]byte{}}+ if tc.archived {+ t.Setenv("TMPDIR", t.TempDir())+ archiveTo(t, bucket)}withoutMasker(t)n := new(atomic.Int64)@@ -85,12 +99,32 @@ func TestUnmaskedRouteIsNotMasked(t *testing.T) {t.Fatalf("masked %d times, want masking %v", n.Load(), tc.masks)}c := s.Recent()[0]- if logged := strings.Contains(c.RequestBody, key); logged != !tc.masks {- t.Fatalf("the log has the key %v, want %v: %s", logged, !tc.masks, c.RequestBody)+ if logged := strings.Contains(c.RequestBody, key); logged != tc.whole {+ t.Fatalf("the log has the key %v, want %v: %s", logged, tc.whole, c.RequestBody)}if c.RequestBody == "" {t.Fatal("the log has no body")}+ if tc.observed {+ obs.mu.Lock()+ got := obs.attempts+ obs.mu.Unlock()+ if len(got) == 0 || !strings.Contains(got[0].BodyIn, placeholder) || strings.Contains(got[0].BodyIn, key) {+ t.Fatalf("the observer was handed %+v", got)+ }+ }+ if tc.archived {+ archivePending.Wait()+ var a Archived+ if err := json.Unmarshal(bucket.objs["archive/"+c.Archive+".json"], &a); err != nil {+ t.Fatalf("%v: %v", keys(bucket.objs), err)+ }+ // as it went: masked, or as written save the secrets every+ // archived body has taken out+ if masked := strings.Contains(a.Request.Body, placeholder); masked == tc.whole || a.Request.Body == "" || strings.Contains(a.Request.Body, key) {+ t.Fatalf("the archive kept %s", a.Request.Body)+ }+ }n.Store(0)f.reply = `{"input_tokens":17}`if code, reply := post(t, "/v1/messages/count_tokens", count); code != 200 {