* fix(stream): normalize delta.reasoning to reasoning_content in SSE streaming
NVIDIA kimi-k2.5 (and potentially other providers) send reasoning
tokens as `delta.reasoning` in SSE streaming chunks instead of the
standard OpenAI `delta.reasoning_content` field. This caused reasoning
content to be silently dropped during stream passthrough — clients
received only the final answer with no reasoning separation.
The non-streaming sanitizer (responseSanitizer.ts) already handled this
alias, but the streaming pipeline did not.
Fix applied in 4 locations:
- stream.ts passthrough: normalize + force re-serialize sanitized chunk
- stream.ts translate: accumulate reasoning from delta.reasoning
- sseParser.ts: collect delta.reasoning in parseSSEToOpenAIResponse
- streamPayloadCollector.ts: collect delta.reasoning in buildOpenAISummary
* fix: eliminate injectedUsage reuse bug and add reasoning alias tests
- Detect delta.reasoning alias before sanitizeStreamingChunk() which
already normalizes it, removing dead post-sanitization normalization
- Replace injectedUsage reuse with separate needsReserialization flag
so reasoning re-serialization cannot block finish_reason/usage
mutations on the same SSE chunk (fixes CRITICAL review finding)
- Add unit test for parseSSEToOpenAIResponse reasoning alias
- Add unit test for buildStreamSummaryFromEvents reasoning alias
* fix(stream): separate reasoning from content in passthrough response body
The passthroughAccumulatedContent variable was mixing delta.content and
delta.reasoning_content into one string, causing the client_response
log and responseBody to lose reasoning separation.
- Add passthroughAccumulatedReasoning accumulator for reasoning deltas
- Set message.reasoning_content in responseBody when reasoning exists
- Only accumulate delta.content into passthroughAccumulatedContent
* fix: trim leading whitespace from assembled content in log summaries
NVIDIA and other providers emit token deltas with leading spaces
(e.g. ' The', ' user'). When joined, these produce a leading space in
the provider_response and parsed non-streaming response logs. Trim
the joined content and reasoning_content in both buildOpenAISummary
and parseSSEToOpenAIResponse for consistent log output.
* fix(stream): split combined reasoning+content deltas into separate SSE events
Some providers (e.g. NVIDIA NIM) send transition chunks with both
`delta.reasoning` and `delta.content` in the same SSE event.
After sanitization this becomes `reasoning_content` + `content`,
which violates the standard OpenAI streaming contract where these
fields are never mixed. Clients using if/else logic (LobeChat, etc.)
skip content when reasoning_content is present, losing the first
content token.
Split such combined chunks into two separate SSE events:
1. Reasoning-only event (finish_reason=null, no usage)
2. Content-only event (carries finish_reason and usage)
* chore(release): v3.2.8 — Docker auto-update UI and cache analytics fixes
* fix(sse): remove race condition in cache metrics tracking (#758)
- Remove in-memory metrics tracking (currentMetrics, trackCacheMetrics, updateCacheMetrics)
- Cache metrics now computed on-the-fly from usage_history table (single source of truth)
- Fixes CRITICAL issue from code review: concurrent requests overwriting metrics
- Fixes WARNING: duplicate metric tracking logic in streaming/non-streaming paths
Ref: PR #752 (merged before this fix was included)
* fix: handle allRateLimited credentials & forward extra body keys in embeddings/images routes (#757)
* fix: handle allRateLimited credentials in embeddings and images routes
When getProviderCredentials() returns an allRateLimited object (truthy,
but without apiKey/accessToken), the embeddings and images routes
incorrectly passed it to handlers as valid credentials. The handlers
then sent upstream requests without Authorization headers, causing
401 errors from providers (e.g. NVIDIA NIM).
This only manifested under concurrent requests: a chat/completions
call could trigger rate limiting on a provider account, and a
simultaneous embeddings request would receive the allRateLimited
sentinel — but treat it as valid credentials.
The chat pipeline already handled this case correctly. This commit
adds the same allRateLimited guard to all affected routes:
- POST /v1/embeddings
- POST /v1/providers/{provider}/embeddings
- POST /v1/images/generations
- POST /v1/providers/{provider}/images/generations
Also adds a defense-in-depth guard in the embeddings handler itself:
if no auth token is available for a non-local provider, return 401
immediately instead of sending an unauthenticated request upstream.
Made-with: Cursor
* fix(embeddings): forward extra body keys to upstream providers
The embeddings handler only forwarded model, input, dimensions, and
encoding_format to upstream providers, silently dropping any additional
fields. This broke asymmetric embedding APIs (e.g. NVIDIA NIM
nv-embedqa-e5-v5) that require input_type, and other providers
expecting user or truncate parameters.
Add a KNOWN_FIELDS exclusion set and forward all unrecognized body
keys to the upstream request, matching the passthrough pattern used
by the chat pipeline's DefaultExecutor.transformRequest().
Made-with: Cursor
* fix(auth): redirect and unconditional 401 on disabled requireLogin + fix test cases
* fix(build): remove legacy proxy.ts causing Next.js build collision
* fix(build): revert middleware.ts rename to proxy.ts because of Next.js Edge constraints
---------
Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com>
Co-authored-by: tombii <tombii@users.noreply.github.com>
Co-authored-by: Gorchakov-Pressure <117600961+Gorchakov-Pressure@users.noreply.github.com>
Cherry-pick from codex/omniroute-fixes-20260324:
- Replace MCP singleton transport with per-session architecture for Streamable HTTP
- Fix Claude passthrough via OpenAI round-trip normalization
- Add detectFormatFromEndpoint() for endpoint-aware format detection
- Support raw code#state in OAuth modal for Claude Code remote auth
- Expose cloudConfigured/cloudUrl/machineId in settings API
- Switch docker-compose.prod.yml target to runner-cli
- Add 3 new tests for round-trip and detectFormat
PR: #562
* feat: add api-key Kimi Coding provider support
* fix(kimi-coding): honor apikey auth header in executor
Ensure DefaultExecutor sends x-api-key for kimi-coding-apikey at runtime
and deduplicate shared kimi coding config blocks in registry and models
config to reduce drift between oauth and apikey variants.
---------
Co-authored-by: OmniRoute Agent <agent@omniroute.local>
Add a default-off dashboard setting that injects Codex fast service tier only when the request did not already specify one.
Also preserve service_tier through OpenAI-to-Responses translation and restore the setting at startup.
Add gpt-5.4 to the Codex model registry so OmniRoute exposes cx/gpt-5.4 and codex/gpt-5.4 in its model catalog.
Includes a focused regression test for model resolution.
OmniRoute is an intelligent API gateway that unifies 20+ AI providers behind a single
OpenAI-compatible endpoint. Features include intelligent routing with 6 strategies,
multi-format translation (OpenAI/Claude/Gemini/Responses API), circuit breakers,
semantic caching, combo fallback chains, real-time health monitoring, and a full
dashboard with provider management, analytics, and CLI tool integration.
Key highlights:
- 20+ providers (Claude Code, Codex, Gemini CLI, GitHub Copilot, iFlow, Qwen, Kiro, etc.)
- 6 routing strategies (Fill First, Round Robin, P2C, Random, Least Used, Cost Optimized)
- Export/Import database backup with full archive support
- Translator Playground with 4 modes (Playground, Chat Tester, Test Bench, Live Monitor)
- 100% TypeScript across src/ and open-sse/
- Docker support with multi-stage builds
- Comprehensive documentation and 9 dashboard screenshots
