chore: bump github.com/maximhq/bifrost/core from 1.7.13 to 1.8.4 in /authbridge/authlib

[dependabot]

Bumps github.com/maximhq/bifrost/core from 1.7.13 to 1.8.4.

Release notes

Sourced from github.com/maximhq/bifrost/core's releases.

Core v1.8.4

Core Release v1.8.4

• fix: strip the encrypted reasoning signature when the upstream reports the field as unsupported (e.g. Bedrock Converse replaying a Claude signature onto a non-Anthropic model after a mid-conversation model switch), extending the existing unverifiable-signature fail-soft
• fix: clear Anthropic raw-body passthrough based on the resolved provider and model pair, so non-Claude models on multi-family providers (Vertex, Azure, Bedrock Mantle) convert the request instead of passing the Anthropic payload through

Installation

go get github.com/maximhq/bifrost/core@v1.8.4

---

This release was automatically created from version file: core/version

Core v1.8.3

Core Release v1.8.3

• fix: forward OpenCode Responses requests directly to /v1/responses @​mohammadrezwankhan
• feat: add the VideoEdit operation with BifrostVideoEditRequest, VideoEditInput and VideoEditParameters for prompt-driven edits, upscaling and background removal on an existing video supplied as bytes, a URL or a provider video ID; implemented for OpenAI (/v1/videos/edits) and Runware (videoInference, upscale, removeBackground), with the model optional when the source is a video ID and the prompt optional for asset-driven task types (#6270)
• feat: batch accounting: MergeBifrostLLMUsage promoted to schemas, Endpoint on BifrostBatchResultsResponse, BatchResultItem.Failed(), BatchRequestCountsFromResults, BatchRequestCounts.IsZero(), raw-JSON Gemini batch result parsing and custom_id validation in ConvertRequestsToJSONL; the settlement engine (AccountBatchResults with runner-ID ownership fencing, idempotent aggregate log writes and governance reporting) and a sweeper that polls due jobs with capped, jittered backoff; aggregate log entries carry a bifrost/<version> user agent via BifrostContextKeyRuntimeVersion (thanks @​SahilChoudhary22!) (#5291, #5294, #6474)
• feat: Claude-on-Vertex batch support: ToVertexBatchCreateRequest resolves Anthropic families to publishers/anthropic/models/..., vertexConvertRequestsToJSONL emits Claude-on-Vertex instances, custom_id round-trips through batchResultsByKey, and GeminiBatchGenerateContentRequest keeps tools, toolConfig, cachedContent, labels and the display name (#5368)
• feat: add HTTPTransportPreAuthHook to the HTTPTransportPlugin interface, a phase that runs before transport authentication; HTTPTransportPreHook now runs after it (#6375) Breaking for plugin authors: Go plugins implementing HTTPTransportPlugin must add HTTPTransportPreAuthHook (.so plugins that predate it are skipped for that phase), and any plugin that injected a credential such as x-bf-vk or Authorization from HTTPTransportPreHook must move that work to HTTPTransportPreAuthHook, since the pre-hook no longer runs before auth.
• feat: add semaphore_size and inject_timeout to PluginConfig so observability Inject calls are context-bounded per plugin (#6341)
• feat: Runware provider expansion: chat completions, streaming and Responses through its OpenAI-compatible /v1/chat/completions endpoint (Responses muxed via ToChatRequest()), ListModels sweeping the curated modelSearch catalog with the AIR as the model ID, image upscale via /v1/images/edits (type=upscale) and image-to-3D via /v1/videos (type=3d), a shared settings extra-param coercion for multipart and JSON callers, prompt-optional asset-driven operations, and input handling for edit, upscale and video task shapes (#6260, #6372, #6208)
• feat: OpenAI ultrafast service tier: BifrostServiceTierUltrafast, capability-gated forwarding via serviceTierForModel on chat, Responses and compaction, and ultrafast preserved through WithDefaults (#6396)
• feat: JSON bodies on /v1/images/edits: ImageInput accepts a bare string or { "url", "image" }, typed extra params reach providers with their real types, and images is a known field (#6418)
• feat: EmbeddingData.EncodingFormat with typed int8, uint8, binary, ubinary and base64 vectors; Bedrock Titan V2 embeddingTypes and Cohere embedding_types on Converse, native invoke and LangChain BedrockEmbeddings compatibility (#6381)
• feat: rerank: RerankDocument.Data for structured documents, RerankResult.ID, RerankParameters.NextToken, ReturnDocuments forwarded to Cohere and Vertex, ToCohereError for Cohere-shaped errors, /genai/v1/rank served cross-provider via x-model-provider, cross-provider responses converted back to the caller's wire shape with ToBedrockRerankResponse, ToCohereRerankResponse and ToVertexRankResponse, and rerank cost accounting for Bedrock and Cohere (#6301, #6328)
• feat: datasheet-backed compatibility flows: Anthropic, Bedrock, Cohere and Gemini request shaping (adaptive-only thinking, adaptive thinking, native effort, disable-reasoning, mid-conversation system turns, computer-use and text-editor tool generations, default max output tokens, tool validation, thinking-budget zeroing) is resolved through schemas.ResolveModelCaps instead of hardcoded model-name checks (#6281, #6492)
• feat: Gemini 3 per-model thinkingLevel support table (geminiThinkingLevelSupport) with clampThinkingLevel snapping requested levels to the nearest rung (ties break upward) and lowestThinkingLevel for reasoning_effort: "none", so setThinkingBudgetZeroIfSupported sets the floor level on Gemini 3+ instead of zeroing thinkingBudget (#6280)
• feat: Bifrost overhead latency accounting: upstream_latency and overhead_latency on BifrostResponseExtraFields (PopulateOverheadLatency, BifrostContextKeyRequestStartTime, populateLatencyExtraFields so logging plugins see both at hook time); per-phase overhead spans across the request pipeline (queue-wait, attribute-population, convertor, request-marshal, response-parse, handle-setup, pipeline-pre, pipeline-post, worker-setup, key-pool, Bedrock request-sign and credentials-fetch, response-finalize) with StampWorkerHandoff on ChannelMessage.sentAt; lock-free stream overhead accumulators for per-chunk parse, conversion and backpressure installed via ResetStreamOverhead, StampStreamTransport for the outbound marshal and client-write time, and defaultSSEDataReader.ReadDataLine attributing socket reads to upstream; and IsOverheadBreakdownSpan, WithoutOverheadBreakdownSpans and the OverheadSpanConsumer interface so breakdown spans stay out of connectors that do not opt in (#5533, #6388, #6389, #6433, #6470, #6495)
• feat: input/output/additional cost split (BifrostCost) on inference usages, extended to speech, transcription and OCR usages
• feat: Notification, NotificationInput, NotificationSeverity, NotificationAudience and the NotificationPublisher function type for the dashboard notification center (#6207)
• feat: BifrostContextKeySkipModelCheck short-circuits the virtual key model allowlist for evaluate-only requests such as /inspect while keeping every other governance rule (#6479)
• feat: HarnessSessionHeaders and MaxSessionIDLength so Claude Code, Codex CLI and OpenCode session headers can fall back into the session ID (#6333)
• feat: RedactSensitiveHeaders, with IsSensitiveHeader extended to Cloudflare Access (cf-access-*), AWS ALB OIDC (x-amzn-oidc-*) and generic jwt/assertion headers (#6371)
• feat: ResponsesResponseError.Type and a shared Responses stream-error normalizer so terminal error/response.failed events inside an HTTP 200 Azure SSE stream surface as errors with their nested type, code and message on both create-stream and retrieve-stream paths (thanks @​dani29!) (#6302)
• feat: ServiceTier on StreamAccumulatorResult, with Anthropic's service_tier from message_start latched onto the final chunk of chat and Responses streams (#6236)
• feat: OpenRouter speech and transcription through the OpenAI-compatible audio handlers instead of returning unsupported-operation errors (#5734)
• fix: preserve max_tokens for OpenCode-compatible chat endpoints (thanks @​Alex-wangyang!) (#6458)
• fix: HuggingFace chat streaming completed with zero tokens and therefore zero cost while non-streaming calls on the same models priced correctly, for two reasons: HuggingFace was listed as a provider that omits the [DONE] marker (it sends one), which made the shared OpenAI streaming loop break on the first finish_reason and discard the trailing usage-only chunk that several router inference providers emit; and stream_options.include_usage never reached the router because the shared streaming handler returns early when a provider supplies a custom request converter. Both are corrected, and an explicit stream_options from the caller still wins (thanks @​elliottrabac!) (#6478)
• fix: preserve the caller's JSON Schema key order for structured outputs - ChatParameters.UnmarshalJSON holds response_format as raw bytes and the new ChatResponseFormat reader splices them verbatim into OpenAI, Anthropic, Bedrock, Gemini (unless a union type array needs normalizing) and Cohere requests, and ResponsesTextConfigFormatJSONSchema re-encodes in the decoded key sequence, because OpenAI structured outputs generate fields in the declared order and a re-sorted schema silently changes model behavior (#6235)
• fix: open reasoning stream items that carry both an encrypted payload and a visible summary as thinking blocks instead of redacted_thinking on the Anthropic egress, with isReasoningItem and reasoningPayloadAndSummary shared by the native-reasoning and misclassified-function-call branches (#6292)
• fix: replayed thinking blocks through the Anthropic ingress with a bedrock/ model prefix: content-less tool_result blocks are kept, interleaved text/tool-use/thinking order is preserved by the grouped converter, incomplete maps to error on Converse toolResult.status, and buffered reasoning is consumed by the item that owns it, so multi-turn tool use no longer wedges (#6346)
• fix: Gemini/Vertex HTTP 400s on Claude Code traffic routed through /anthropic/v1/messages: trailing assistant prefills are trimmed on both the Responses and chat paths, mid-conversation system messages are inlined in place instead of hoisted into systemInstruction, and AnthropicMessageResponse gains ExtraFields (#6363)
• fix: alias Bedrock toolUseId/toolResultId values longer than 64 characters or outside [a-zA-Z0-9_.:-] (such as Gemini thought-signature IDs) with a deterministic hash prefix, applied identically on tool_use and tool_result in both the Responses and chat converters (#6300)

... (truncated)

Commits

• 6d60595 core changelog for the release cut (#6605) --skip-ci
• ce56d2d core changelog (#6603)
• b36efdb core changelog
• 9157baf core version bump (#6601) --skip-core-test
• 02aee90 core version bump (#6599)
• 16d4220 docs: document KMS-encrypted S3 buckets for log object storage (#6497)
• e4a7d3c fix: unsupported reasoning signature to be stripped (#6593)
• 935e759 fix: unsupported reasoning signature to be stripped
• 1cd3635 fix: clear passthrough for non claude models in non native claude model provi...
• 141e9ed fix: clear passthrough for non claude models in non native claude model provi...
• Additional commits viewable in compare view

[dependabot]

OK, I won't notify you again about this release, but will get in touch when a new version is available. If you'd rather skip all updates until the next major or minor version, let me know by commenting @dependabot ignore this major version or @dependabot ignore this minor version. You can also ignore all major, minor, or patch releases for a dependency by adding an ignore condition with the desired update_types to your config file.

If you change your mind, just re-open this PR and I'll resolve any conflicts on it.

[huang195]

Superseded by #840, which takes v1.7.15 instead — the last release that does not force a Go toolchain migration.

Why this failed: bifrost v1.8.0 raised its own go directive to 1.27.0, and Go propagates that into every module in the workspace. So this PR rewrote go 1.26.5 → go 1.27.0 in all seven go.mod files while authbridge/go.work stayed at 1.26.5:

go: module . listed in go.work file requires go >= 1.27.0,
    but go.work lists go 1.26.5

That also explains the odd file list here — seven go.mod edits but only three matching go.sum, because most modules changed only their go directive.

The version boundary:

bifrost/core	go directive
v1.7.13 (current)	go 1.26.5
v1.7.14, v1.7.15	go 1.26.5
v1.8.0 → v1.8.4	go 1.27.0

v1.7.15 gets two patch releases with no toolchain change. Dependabot only proposes the newest version, so that middle ground never surfaced.

What v1.8.x would actually cost — not the one-line go.work bump it looks like. Also the four digest-pinned golang:1.26-alpine builders in cmd/authbridge-{envoy,proxy,praxis,cpex}/Dockerfile. Those set GOWORK=off but not GOTOOLCHAIN, so they would not fail — they would silently download the 1.27 toolchain mid-build and ship images where a pinned 1.26 base bootstraps an unpinned 1.27. Plus every developer moving to Go 1.27.0.

And it buys nothing today: authlib touches exactly three bifrost symbols — bschemas.ModelProvider, bschemas.Anthropic, bschemas.OpenAI — in one six-line function in plugins/contextguru/plugin.go. Nothing in bifrost 1.8 is reachable from our code, and this is not a security update.

Good news for later: I built and tested v1.8.4 locally with go.work at 1.27.0 and the full authlib suite passed (48 packages). There is no API break waiting — whenever the Go 1.27 move happens deliberately, it is purely a toolchain exercise.

#838 gates >=1.8.0 in .github/dependabot.yml so v1.8.x is not re-proposed weekly while 1.7.x patches keep flowing.

Assisted-By: Claude Code