* test(relayconvert): add golden snapshot matrix and relaykit boundary guard
Phase 0 of the relaykit extraction plan: pin byte-level output of every
registered (from,to) request/response/stream conversion route, and
forbid kit-bound packages from growing host-only imports.
* wip(relayconvert): drop gin.Context from converter signatures; add convmeta draft
Phase 1 in progress: relayconvert now takes context.Context; host media
resolver adapts gin.Context back at the service boundary.
* refactor(relayconvert): decouple converters from RelayInfo, gin, and settings
Phase 1 of the relaykit extraction plan:
- converters now depend on convmeta.Meta (implemented by RelayInfo) instead
of *relaycommon.RelayInfo; ClaudeConvertInfo and the format guesser move
to convmeta with aliases left behind
- host settings reach converters via a convmeta.Options snapshot built in
RelayInfo.ConvOptions; no more model_setting/reasoning global reads inside
the conversion layer
- effort-suffix helpers move to service/relayconvert/reasoning (old package
forwards); chat-to-responses upgrade policy moves to service (host routing
logic, not conversion)
- golden conversion matrix unchanged
* test(relayconvert): tighten boundary — kit packages now free of gin/setting imports
* refactor(dto): drop gin and logger dependencies
Phase 2 (part 1): dto.Request.IsStream now takes *http.Request instead of
*gin.Context (Gemini's impl reads query/path off the std request); dto's
three logger calls become common.SysError. Boundary test allowlist is now
empty — kit-bound packages import no gin/setting/logger/model.
* refactor(kit): extract dependency-free kitutil; dto/types/relayconvert stop importing common
Phase 2 of the relaykit extraction plan:
- new service/relayconvert/kitutil holds the pure helpers the kit needs
(JSON wrappers, pointer/string/uuid/timestamp utils, MaskSensitiveInfo,
pluggable LogInfo/LogError hooks, Debug flag)
- dto, types, and all relayconvert packages now use kitutil; their only
remaining internal deps are dto/types/constant
- common keeps every original symbol (MaskSensitiveInfo delegates to
kitutil) so host code is untouched; main.go routes kit logging into
common.SysLog/SysError and mirrors DebugEnabled
- golden conversion matrix unchanged
* refactor(kit): move EndpointType/FinishReason to types; OpenRouter dialect via Options
Kit packages (dto/types/relayconvert/reasonmap) no longer import constant:
- EndpointType and finish-reason values live in types; constant re-exports
- the OpenRouter special-case in claude->openai request conversion reads
Options.OpenRouterDialect, set by the host from the channel type;
InitChannelMeta invalidates the cached snapshot on channel switch
* refactor: extract relaykit submodule (dto/types/relayconvert/reasonmap)
Phase 3 of the relaykit extraction plan:
- new go module github.com/QuantumNous/new-api/relaykit containing dto
(minus task family), types, relayconvert (with convmeta/kitutil/reasoning),
and reasonmap; host consumes it via require + replace, go.work for dev
- task-family dto (task/suno/midjourney/video) stays in the host dto
package; dual-consumer host files alias it as taskdto
- relaykit builds and tests standalone (GOWORK=off): no host imports,
no gin, no DB, no settings
- golden conversion matrix unchanged
* build(docker): copy relaykit/go.mod before go mod download
The local-replace submodule's go.mod must exist inside the build context
for the main module graph to resolve.
* fix: address relaykit extraction regressions
* fix: address relaykit review regressions
* docs: document Meta nil receiver contract
* fix(relaykit): fail OpenAI→Claude conversion without max_tokens; reject negative default_max_tokens
The Claude Messages API requires max_tokens (omitting it is a 400
"Field required"), but with a nil Options.Claude.DefaultMaxTokens hook
the converters silently emitted a request the upstream is guaranteed to
reject. Both OpenAI Chat and Responses → Claude conversions now return
sharedclaude.ErrMissingMaxTokens when no path (client value, default
hook, thinking-adapter floor) supplied one. Unreachable in the host,
which always configures the hook.
Host side, claude.default_max_tokens now rejects negative values at the
option API before persisting — they would wrap into huge unsigned values
during conversion. Zero stays allowed: the current API treats
max_tokens: 0 as cache pre-warming.
* fix: make Gemini safety settings read path race-free
Bound max-tokens fields across all relay format validators, saturate
tiered-expression rounding and audio/tool/task token conversions, and
route legacy remix ratios through the guarded setter.
Bound user-supplied count/duration parameters at request validation,
route ratio multipliers through guarded setters, and use saturating
int conversions in all quota math paths.
* fix: avoid stale stream writes after client disconnect
* fix: wait for stream ping goroutines before returning
* fix: log stream results after goroutine cleanup
* fix: broadcast stream stop signals
* fix: abort upstream on client disconnect and restore write error contracts
Keep the goroutine-lifecycle fix (unconditional wg.Wait before returning the
gin.Context, close resp.Body inside cleanup), but drop the drain-on-disconnect
behavior: when the client goes away, cleanup now runs immediately so the
upstream body is closed, the provider stops generating, and users are not
billed for tokens produced after they disconnected.
Also restore FlushWriter/StringData/PingData returning an error when the
request context is done, so non-scanner relay loops (ollama, fake-stream,
audio, image) keep their disconnect awareness instead of silently consuming
the upstream to completion. ResponseChunkData now propagates write errors.
Add a bounded per-write deadline (http.NewResponseController) before each
locked stream write so a slow-but-connected client cannot block a write
forever and hang the unconditional wg.Wait.
---------
Co-authored-by: CaIon <i@caion.me>
Route OpenAI image streaming through shared stream handling, split image/realtime/usage helpers for maintainability, and include the related image request and rate limit updates.
- quota.go: add missing SettleBilling call in PostWssConsumeQuota
- text_quota.go: gate InjectTieredBillingInfo on tieredBillingApplied bool
instead of tieredResult != nil, so fallback billing still logs metadata
- price.go: remove quotaBeforeGroup == 0 from freeModel condition to avoid
bypassing settlement for output-only expressions
- tiered_settle.go: split cc/cc1h subtraction using UsageSemantic to
distinguish OpenAI vs Claude cache creation token formats
- pricing.go: only set BillingMode when a non-empty expression exists
- useModelPricingEditorState.js: only write billing_mode when
finalBillingExpr is non-empty
- Backend: differentiate error messages for admin vs regular users in price.go
- Backend: include error_code in channel test response for structured error handling
- Frontend: render model_price_error as a styled card in Playground with admin nav button
- Frontend: show inline error details and settings link in channel test modal
- Frontend: parse error codes from both SSE and non-streaming API responses
- i18n: remove redundant "Settings" suffix from setting tab translations (en/fr/ru/ja/vi)
- i18n: update "Group & Model Pricing" translations across all locales
Pre-fill BillingRequestInput from dto.Request before ModelPriceHelper,
so tiered_expr billing resolves param() from the structured request
instead of reading HTTP body (which is empty in channel-test context).
- attachTestBillingRequestInput: marshal dto.Request → RequestInput
- ResolveIncomingBillingExprRequestInput: early-return when pre-filled
- settleTestQuota / buildTestLogOther: align test settlement & logging
with production TryTieredSettle / InjectTieredBillingInfo paths
- Added `EstimateBilling` function to check for video input in request metadata and return corresponding discount ratios.
- Updated `ModelPriceHelperPerCall` to incorporate new pricing logic based on model ratios and video input.
- Enhanced task billing logs to include model ratio information and adjusted calculations for actual quota based on additional multipliers.
- Introduced `renderTaskBillingProcess` to improve rendering of task billing information in the UI.
- Add StreamStatus type (relay/common) to track stream end reason
(done/timeout/client_gone/scanner_error/eof/panic/ping_fail) and
accumulate soft errors during streaming via sync.Once + sync.Mutex.
- Add StreamResult (relay/helper) as the callback interface: adapters
call sr.Error() for soft errors, sr.Stop() for fatal, sr.Done() for
normal completion. No early-return problem — multiple errors per chunk
are naturally supported.
- Refactor StreamScannerHandler callback from func(string) bool to
func(string, *StreamResult). All 9 channel adapters updated.
- Write stream_status into log other JSON field (admin-only) with
status ok/error, end_reason, error_count, and error messages.
- Frontend: display stream status in log detail expansion for admins.
- Introduced a new rule for the Billing Expression System, emphasizing the importance of reading `pkg/billingexpr/expr.md` for dynamic billing.
- Updated the billing expression logic to support new variables and improved handling of image and audio tokens.
- Enhanced the tiered billing functionality with versioning support for expressions and refined quota calculations.
- Added tests to validate the new billing expression features and ensure correctness in pricing calculations.
- Adjusted billing calculations in tests and core logic to incorporate a new QuotaPerUnit field.
- Modified estimated quota calculations to reflect changes in tiered billing logic.
- Updated related tests to ensure accuracy with the new quota calculations.
- Enhanced dynamic pricing components to align with updated billing expressions.
- Added support for tiered billing expressions in the billing system.
- Introduced new types and functions for handling billing expressions, including caching and execution.
- Updated existing billing logic to accommodate tiered billing scenarios.
- Enhanced request handling to support incoming billing expression requests.
- Added tests for tiered billing functionality to ensure correctness.
#3079
Change ModelPriceHelperPerCall to return (PriceData, error) and stop silently falling back to a default price. If a model price is not configured the helper now returns an error (unless the user has AcceptUnsetRatioModel enabled and a ratio exists). Propagate this error to callers: Midjourney handlers now return a MidjourneyResponse with Code 4 and the error message, and task submission returns a wrapped task error with HTTP 400. Also extract remix video_id in ResolveOriginTask for remix actions. This enforces explicit model price/ratio configuration and surfaces configuration issues to clients.
- Introduced a new test file for StreamScannerHandler, covering various scenarios including nil inputs, empty bodies, chunk processing, order preservation, and handler failures.
- Enhanced error handling and data processing logic in StreamScannerHandler to improve robustness and performance.
Restructure the task relay system for better separation of concerns:
- Extract task billing into service/task_billing.go with unified settlement flow
- Move task polling loop from controller to service/task_polling.go (supports Suno + video platforms)
- Split RelayTask into fetch/submit paths with dedicated retry logic (taskSubmitWithRetry)
- Add TaskDto, TaskResponse generics, and FetchReq to dto/task.go
- Add taskcommon/helpers.go for shared task adaptor utilities
- Remove controller/task_video.go (logic consolidated into service layer)
- Update all task adaptors (ali, doubao, gemini, hailuo, jimeng, kling, sora, suno, vertex, vidu)
- Simplify frontend task logs to use new TaskDto response format
CaIon