npm version patch run BEFORE staging files — this is an ATOMIC commit.
Adds Strategy 1.5 to scripts/postinstall.mjs:
- Uses @mapbox/node-pre-gyp install --fallback-to-build=false
(bundled within better-sqlite3) to download the correct prebuilt
binary for the current OS/arch (win32-x64/arm64, darwin-x64/arm64)
WITHOUT requiring node-gyp, Python, or MSVC build tools.
- Tries node-pre-gyp.cmd (Windows) or node-pre-gyp (Unix) from .bin/
with fallback to direct path in @mapbox/node-pre-gyp/bin/
- Falls back to npm rebuild only if prebuilt download fails.
- Windows-specific error: shows Option A (npx node-pre-gyp) and
Option B (rebuild) with Visual Studio Build Tools links.
Fixes: #426 (better_sqlite3.node is not a valid Win32 application)
Includes version bump — v2.6.9 — committed ATOMICALLY with all changes:
fixes:
- fix(ci/t11): Remove 'any' from comments in openai-responses.ts + chatCore.ts
(\bany\b regex counted comment text as explicit any violations)
- fix(chatCore/#409): Normalize unsupported content part types before forwarding
Cursor sends {type:'file'} for .md attachments; Copilot/OpenAI providers reject
with 'type has to be either image_url or text'. Now: file/document→text block,
unknown types dropped with debug log. Fixes claude-* models via github-copilot.
workflow:
- chore(generate-release): ATOMIC COMMIT RULE — npm version patch MUST run before
feature commits so the release tag always points to a commit with full changes
DB Migrations (zero-breaking, ADD COLUMN DEFAULT NULL + new table):
- 005_combo_agent_fields.sql: system_message, tool_filter_regex, context_cache_protection on combos
- 006_detailed_request_logs.sql: ring-buffer table (500 entries) for full pipeline body capture
Features:
- #399 System Message Override + Tool Filter Regex per Combo
- applyComboAgentMiddleware() injected into handleComboChat/handleRoundRobinCombo
- Supports both OpenAI and Anthropic tool name formats
- #401 Context Caching Protection (Stateless)
- injectModelTag() appends <omniModel>provider/model</omniModel> to responses
- extractPinnedModel() reads tag from history and pins model for session
- #320 Auto-Update via Settings
- GET /api/system/version — current vs latest npm
- POST /api/system/update — fire-and-forget npm install + pm2 restart
- #378 Detailed Request Logs
- saveRequestDetailLog() captures bodies at 4 pipeline stages (opt-in toggle)
- GET/POST /api/logs/detail — list logs + enable/disable toggle
- #336 MITM Kiro IDE
- src/mitm/targets/kiro.ts: MitmTarget profile for api.anthropic.com interception
Audio endpoints (/v1/audio/speech and /v1/audio/transcriptions) only
supported hardcoded providers from audioRegistry.ts. Local inference
backends configured as provider_nodes (e.g., MLX-Audio, oMLX) could
not serve audio through OmniRoute.
This adds a Phase 3 fallback in the audio model parser that consults
provider_nodes from the database. Local providers with api_type=openai
are automatically available for audio routing via their prefix
(e.g., mlx-audio/tts-model, omlx/whisper-large-v3-turbo).
Design: injection pattern — Next.js route handlers load provider_nodes
(async DB query) and pass them to the sync parser as a parameter.
No cross-workspace imports, no breaking changes to existing parsers.
Changes:
- Add buildDynamicAudioProvider() in audioRegistry.ts
- Add Phase 3 (provider_nodes prefix match) to parseAudioModel()
- Extend parseSpeechModel/parseTranscriptionModel with optional
dynamicProviders parameter (backward compatible)
- Load and inject provider_nodes in speech/transcription route handlers
- Dynamic providers use authType=none (local, no credentials needed)
Claude OAuth tokens are short-lived and require refresh. The runtime
HealthCheck (open-sse) already refreshes them successfully, but the
Dashboard test endpoint was missing `refreshable: true` in its config.
This caused the Dashboard to show "auth failed / Token expired" for
Claude providers even though the tokens were being refreshed correctly
at runtime. The codex provider already had this flag set.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Anthropic API rejects requests containing {"type":"text","text":""} with
400 "text content blocks must be non-empty". Some clients like LiteLLM
passthrough and @ai-sdk/anthropic may forward empty text blocks as-is.
Filter out empty text content blocks from messages before calling
translateRequest, similar to how empty-name tools are already stripped.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- gemini/gemini-cli: removed gemini-3.1-pro/flash/preview (don't exist in Google API v1beta),
replaced with real models: gemini-2.5-pro, gemini-2.5-flash, gemini-2.0-flash, gemini-1.5-*
- antigravity: removed gemini-3.1-pro-high/low and gemini-3-flash (internal aliases invalid),
replaced with gemini-2.5-pro, gemini-2.5-flash, gemini-2.0-flash
- github: removed gemini-3-flash-preview and gemini-3-pro-preview, replaced with gemini-2.5-flash
- nvidia: corrected 'nvidia/llama-3.3-70b-instruct' to 'meta/llama-3.3-70b-instruct'
(NVIDIA NIM uses meta/ namespace, not nvidia/ namespace for Meta models)
- nvidia: added meta/llama-3.1-70b-instruct and nvidia/llama-3.1-405b-instruct
Also fixed free-stack combo on .15 DB:
- removed qw/qwen3-coder-plus (qwen provider has expired refresh token)
- corrected nvidia/llama-3.3-70b-instruct → nvidia/meta/llama-3.3-70b-instruct
- corrected gemini/gemini-3.1-flash → gemini/gemini-2.5-flash
- added if/deepseek-v3.2 as replacement for qw/qwen3-coder-plus
Local inference backends (oMLX, Ollama, LM Studio) configured as
provider_nodes have no health monitoring. When a local provider is
down, OmniRoute waits the full timeout before failing.
This adds a background health check that polls local provider_nodes:
- GET /models with 5s timeout for each local node (localhost only)
- In-memory health cache (no DB migration needed)
- Promise.allSettled for parallel checks (one slow node doesn't block)
- Exponential backoff on failures: 30s → 60s → 120s → 300s max
- Reset to 30s on first success after failure
- State transition logging (healthy ↔ unhealthy)
- Expose health status via GET /api/monitoring/health (localProviders)
- Auto-init on first import (same pattern as tokenHealthCheck)
- 401 treated as healthy (server up, auth required)
- isNodeHealthy() returns true if never checked (optimistic default)
Embedding endpoint (/v1/embeddings) only supports 6 hardcoded cloud
providers. Local inference backends (oMLX, Ollama) serving embeddings
via provider_nodes are inaccessible through OmniRoute.
This adds dynamic provider_node support for embeddings:
- Add EmbeddingProvider interface and buildDynamicEmbeddingProvider()
- Add Phase 2 (provider_nodes prefix match) in parseEmbeddingModel()
- Handler accepts resolvedProvider/resolvedModel from route (injection pattern)
- Handler supports authType=none for local providers (was missing — critical gap)
- Route loads local provider_nodes (localhost only — prevents auth bypass/SSRF)
- Route filters by apiType=chat|responses and localhost hostname
- buildDynamicEmbeddingProvider validates inputs (prefix + baseUrl required)
- Per-node try/catch in map — one bad row doesn't block all providers
- DB errors logged and fall back to hardcoded providers
Use shallow copy ({ ...body }) instead of direct reference assignment
so that later translatedBody.model = model does not mutate the
caller's original body object.
When both source and target formats are Claude, skip all request
modification and forward the body untouched. This prevents
prepareClaudeRequest from corrupting valid Claude-native requests
destined for anthropic-compatible provider nodes.
When Claude Code compacts conversation context to fit within token
limits, it may remove assistant messages containing tool_use/tool_calls
while leaving the corresponding tool_result/function_call_output
messages intact. This creates orphaned tool results that cause
providers to reject requests with errors like "tool result's tool id
not found" or "No tool call found for function call output".
Prevents infinite retry loops when models generate tool calls with
empty function names. The normalizeToolName function converted these
to "placeholder_tool" which does not exist in any client's tool
registry, causing repeated error-retry cycles.
